docker/unified: publish rootless image variant (#630)

Keep request duration from being underreported when upstream timings
only cover part of the full request lifecycle.

- compare wall-clock and upstream timing durations
- keep token and throughput values from timings
- add regression coverage for underreported timings

fixes #602

.github/workflows/config-schema.yml

@@ -4,11 +4,15 @@ on:
   pull_request:
     paths:
       - "config-schema.json"
+      - "config.example.yaml"
+      - ".github/workflows/config-schema.yml"
   push:
     branches:
       - main
     paths:
       - "config-schema.json"
+      - "config.example.yaml"
+      - ".github/workflows/config-schema.yml"
 
   workflow_dispatch:
 
@@ -39,3 +43,14 @@ jobs:
           fi
 
           echo "✓ config-schema.json is valid"
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.x"
+
+      - name: Install check-jsonschema
+        run: pip install check-jsonschema
+
+      - name: Validate config.example.yaml against schema
+        run: check-jsonschema --schemafile config-schema.json config.example.yaml

.github/workflows/containers.yml

@@ -29,7 +29,7 @@ jobs:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        platform: [intel, cuda, vulkan, cpu, musa, rocm]
+        platform: [intel, cuda, cuda13, vulkan, cpu, musa, rocm]
       fail-fast: false
     steps:
       - name: Checkout code

.github/workflows/go-ci.yml

@@ -36,7 +36,7 @@ jobs:
     - name: Set up Go
       uses: actions/setup-go@v4
       with:
-        go-version: '1.23'
+        go-version-file: go.mod
 
     # Only run in this linux based runner
     - name: Check Formatting
@@ -51,7 +51,7 @@ jobs:
       uses: actions/cache/restore@v4
       with:
         path: ./build
-        key: ${{ runner.os }}-simple-responder-${{ hashFiles('misc/simple-responder/simple-responder.go') }}
+        key: ${{ runner.os }}-simple-responder-${{ hashFiles('cmd/simple-responder/simple-responder.go') }}
 
     # necessary for testing proxy/Process swapping
     - name: Create simple-responder
@@ -67,4 +67,4 @@ jobs:
         key: ${{ runner.os }}-simple-responder-${{ hashFiles('misc/simple-responder/simple-responder.go') }}
 
     - name: Test all
-      run: make test-all
+      run: make test-all

.github/workflows/unified-docker.yml

@@ -0,0 +1,133 @@
+name: Build Unified Docker Image
+
+on:
+  schedule:
+    - cron: "37 5 * * *"
+
+  workflow_dispatch:
+    inputs:
+      llama_cpp_ref:
+        description: "llama.cpp commit hash, tag, or branch"
+        required: false
+        default: "master"
+      whisper_ref:
+        description: "whisper.cpp commit hash, tag, or branch"
+        required: false
+        default: "master"
+      sd_ref:
+        description: "stable-diffusion.cpp commit hash, tag, or branch"
+        required: false
+        default: "master"
+      ik_llama_ref:
+        description: "ik_llama.cpp commit hash, tag, or branch (CUDA only)"
+        required: false
+        default: "main"
+      llama_swap_version:
+        description: "llama-swap version (e.g. v198, latest, main)"
+        required: false
+        default: "main"
+      build_cuda:
+        description: "Build CUDA image"
+        type: boolean
+        required: false
+        default: true
+      build_vulkan:
+        description: "Build Vulkan image"
+        type: boolean
+        required: false
+        default: true
+
+permissions:
+  contents: read
+  packages: write
+
+jobs:
+  setup:
+    runs-on: ubuntu-latest
+    outputs:
+      matrix: ${{ steps.set-matrix.outputs.matrix }}
+    steps:
+      - id: set-matrix
+        run: |
+          backends=()
+          # schedule uses defaults (build both); workflow_dispatch respects inputs
+          if [[ "${{ github.event_name }}" == "schedule" ]] || [[ "${{ inputs.build_cuda }}" == "true" ]]; then
+            backends+=("cuda")
+          fi
+          if [[ "${{ github.event_name }}" == "schedule" ]] || [[ "${{ inputs.build_vulkan }}" == "true" ]]; then
+            backends+=("vulkan")
+          fi
+          matrix=$(printf '%s\n' "${backends[@]}" | jq -R . | jq -sc .)
+          echo "matrix=$matrix" >> $GITHUB_OUTPUT
+
+  build:
+    needs: setup
+    if: ${{ needs.setup.outputs.matrix != '[]' }}
+    runs-on: ubuntu-latest
+    strategy:
+      fail-fast: false
+      matrix:
+        backend: ${{ fromJSON(needs.setup.outputs.matrix) }}
+        variant:
+          - name: root
+            uid: "0"
+            suffix: ""
+          - name: rootless
+            uid: "10001"
+            suffix: "-rootless"
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Free up disk space
+        run: |
+          echo "Before cleanup:"
+          df -h
+          sudo rm -rf /usr/share/dotnet
+          sudo rm -rf /usr/local/lib/android
+          sudo rm -rf /opt/ghc
+          sudo rm -rf /opt/hostedtoolcache/CodeQL
+          sudo docker system prune -af
+          echo "After cleanup:"
+          df -h
+
+      # On GitHub Actions runners, create a fresh builder.
+      # When running locally under act, skip this and reuse the existing
+      # llama-swap-builder (which has ccache warm) to avoid exhausting disk.
+      - name: Set up Docker Buildx
+        if: ${{ !env.ACT }}
+        uses: docker/setup-buildx-action@v3
+
+      - name: Log in to GitHub Container Registry
+        if: ${{ !env.ACT }}
+        uses: docker/login-action@v3
+        with:
+          registry: ghcr.io
+          username: ${{ github.actor }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Build unified Docker image (${{ matrix.backend }}, ${{ matrix.variant.name }})
+        env:
+          LLAMA_REF: ${{ inputs.llama_cpp_ref || 'master' }}
+          WHISPER_REF: ${{ inputs.whisper_ref || 'master' }}
+          SD_REF: ${{ inputs.sd_ref || 'master' }}
+          IK_LLAMA_REF: ${{ inputs.ik_llama_ref || 'main' }}
+          LS_VERSION: ${{ inputs.llama_swap_version || 'main' }}
+          RUN_UID: ${{ matrix.variant.uid }}
+          DOCKER_IMAGE_TAG: ghcr.io/mostlygeek/llama-swap:unified-${{ matrix.backend }}${{ matrix.variant.suffix }}
+          # When running under act, use the local builder that has warm ccache.
+          # On GitHub Actions, BUILDX_BUILDER is unset so docker uses the builder
+          # created by setup-buildx-action above.
+          BUILDX_BUILDER: ${{ env.ACT == 'true' && 'llama-swap-builder' || '' }}
+        run: |
+          chmod +x docker/unified/build-image.sh
+          docker/unified/build-image.sh --${{ matrix.backend }}
+
+      - name: Push to GitHub Container Registry
+        if: ${{ !env.ACT }}
+        run: |
+          TAG="ghcr.io/mostlygeek/llama-swap:unified-${{ matrix.backend }}${{ matrix.variant.suffix }}"
+          docker push "${TAG}"
+          DATE_TAG=$(date -u +%Y-%m-%d)
+          docker tag "${TAG}" "${TAG}-${DATE_TAG}"
+          docker push "${TAG}-${DATE_TAG}"

AGENTS.md

@@ -21,6 +21,7 @@ llama-swap is a light weight, transparent proxy server that provides automatic m
 
 - Follow test naming conventions like `TestProxyManager_<test name>`, `TestProcessGroup_<test name>`, etc.
 - Use `go test -v -run <name pattern for new tests>` to run any new tests you've written.
+- Run `gofmt -l .` before committing to verify formatting. Fix any reported files with `gofmt -w <file>`.
 - Use `make test-dev` after running new tests for a quick over all test run. This runs `go test` and `staticcheck`. Fix any static checking errors. Use this only when changes are made to any code under the `proxy/` directory
 - Use `make test-all` before completing work. This includes long running concurrency tests.
 

Makefile

@@ -51,7 +51,7 @@ mac: ui
 linux: ui
 	@echo "Building Linux binary..."
 	GOOS=linux GOARCH=amd64 go build -ldflags="-X main.commit=${GIT_HASH} -X main.version=local_${GIT_HASH} -X main.date=${BUILD_DATE}" -o $(BUILD_DIR)/$(APP_NAME)-linux-amd64
-	GOOS=linux GOARCH=arm64 go build -ldflags="-X main.commit=${GIT_HASH} -X main.version=local_${GIT_HASH} -X main.date=${BUILD_DATE}" -o $(BUILD_DIR)/$(APP_NAME)-linux-arm64
+#GOOS=linux GOARCH=arm64 go build -ldflags="-X main.commit=${GIT_HASH} -X main.version=local_${GIT_HASH} -X main.date=${BUILD_DATE}" -o $(BUILD_DIR)/$(APP_NAME)-linux-arm64
 
 # Build Windows binary
 windows: ui

README.md

@@ -32,6 +32,10 @@ Built in Go for performance and simplicity, llama-swap has zero dependencies and
   - `v1/rerank`, `v1/reranking`, `/rerank`
   - `/infill` - for code infilling
   - `/completion` - for completion endpoint
+- ✅ SDAPI via [stable-diffusion.cpp's server](https://github.com/leejet/stable-diffusion.cpp/tree/master/examples/server)
+  - `/sdapi/v1/txt2img`
+  - `/sdapi/v1/img2img`
+  - `/sdapi/v1/loras` - requires `model` in request body to fetch the correct loras
 - ✅ llama-swap API
   - `/ui` - web UI
   - `/upstream/:model_id` - direct access to upstream server ([demo](https://github.com/mostlygeek/llama-swap/pull/31))

cmd/simple-responder/simple-responder.go

@@ -274,6 +274,43 @@ func main() {
 		c.String(200, fmt.Sprintf("%s %s", c.Request.Method, c.Request.URL.Path))
 	})
 
+	// SD API endpoints
+	r.POST("/sdapi/v1/txt2img", func(c *gin.Context) {
+		body, err := io.ReadAll(c.Request.Body)
+		if err != nil {
+			c.JSON(http.StatusInternalServerError, gin.H{"error": "Failed to read request body"})
+			return
+		}
+		defer c.Request.Body.Close()
+
+		modelName := gjson.GetBytes(body, "model").String()
+		c.JSON(http.StatusOK, gin.H{
+			"model":  modelName,
+			"images": []string{},
+		})
+	})
+
+	r.POST("/sdapi/v1/img2img", func(c *gin.Context) {
+		body, err := io.ReadAll(c.Request.Body)
+		if err != nil {
+			c.JSON(http.StatusInternalServerError, gin.H{"error": "Failed to read request body"})
+			return
+		}
+		defer c.Request.Body.Close()
+
+		modelName := gjson.GetBytes(body, "model").String()
+		c.JSON(http.StatusOK, gin.H{
+			"model":  modelName,
+			"images": []string{},
+		})
+	})
+
+	r.GET("/sdapi/v1/loras", func(c *gin.Context) {
+		c.JSON(http.StatusOK, gin.H{
+			"loras": []string{},
+		})
+	})
+
 	address := "127.0.0.1:" + *port // Address with the specified port
 
 	srv := &http.Server{

config-schema.json

@@ -39,6 +39,43 @@
             },
             "default": {},
             "description": "A dictionary of string substitutions. Macros are reusable snippets used in model cmd, cmdStop, proxy, checkEndpoint, filters.stripParams. Macro names must be <64 chars, match ^[a-zA-Z0-9_-]+$, and not be PORT or MODEL_ID. Values can be string, number, or boolean. Macros can reference other macros defined before them."
+        },
+        "timeouts": {
+            "type": "object",
+            "properties": {
+                "connect": {
+                    "type": "integer",
+                    "minimum": 0,
+                    "default": 30,
+                    "description": "TCP connection timeout in seconds. Set to 0 to disable (not recommended)."
+                },
+                "responseHeader": {
+                    "type": "integer",
+                    "minimum": 0,
+                    "default": 60,
+                    "description": "Time to wait for response headers in seconds. Set to 0 to disable (not recommended)."
+                },
+                "tlsHandshake": {
+                    "type": "integer",
+                    "minimum": 0,
+                    "default": 10,
+                    "description": "TLS handshake timeout in seconds. Set to 0 to disable (not recommended)."
+                },
+                "expectContinue": {
+                    "type": "integer",
+                    "minimum": 0,
+                    "default": 1,
+                    "description": "Expect-Continue timeout in seconds. Set to 0 to disable (not recommended)."
+                },
+                "idleConn": {
+                    "type": "integer",
+                    "minimum": 0,
+                    "default": 90,
+                    "description": "Idle connection timeout in seconds. Set to 0 to disable (not recommended)."
+                }
+            },
+            "additionalProperties": false,
+            "description": "Timeout settings for proxy connections."
         }
     },
     "properties": {
@@ -48,6 +85,12 @@
             "default": 120,
             "description": "Number of seconds to wait for a model to be ready to serve requests."
         },
+        "globalTTL": {
+            "type": "integer",
+            "minimum": 0,
+            "default": 0,
+            "description": "Default TTL for all models in seconds, 0 means no TTL and models will never be automatically unloaded"
+        },
         "logLevel": {
             "type": "string",
             "enum": [
@@ -177,9 +220,9 @@
                     },
                     "ttl": {
                         "type": "integer",
-                        "minimum": 0,
-                        "default": 0,
-                        "description": "Automatically unload the model after ttl seconds. 0 disables unloading. Must be >0 to enable."
+                        "minimum": -1,
+                        "default": -1,
+                        "description": "Automatically unload the model after ttl seconds. -1 uses the global TTL value, 0 disables unloading. Must be >0 to enable."
                     },
                     "useModelName": {
                         "type": "string",
@@ -235,6 +278,9 @@
                         "type": "boolean",
                         "default": false,
                         "description": "If true the model will not show up in /v1/models responses. It can still be used as normal in API requests."
+                    },
+                    "timeouts": {
+                        "$ref": "#/definitions/timeouts"
                     }
                 }
             }
@@ -361,6 +407,37 @@
                         "additionalProperties": false,
                         "default": {},
                         "description": "Dictionary of filter settings for peer requests. Supports stripParams and setParams."
+                    },
+                    "timeouts": {
+                        "type": "object",
+                        "properties": {
+                            "connect": {
+                                "type": "integer",
+                                "minimum": 1,
+                                "default": 30,
+                                "description": "TCP connection timeout in seconds."
+                            },
+                            "responseHeader": {
+                                "type": "integer",
+                                "minimum": 1,
+                                "default": 60,
+                                "description": "Time to wait for response headers in seconds."
+                            },
+                            "tlsHandshake": {
+                                "type": "integer",
+                                "minimum": 1,
+                                "default": 10,
+                                "description": "TLS handshake timeout in seconds."
+                            },
+                            "idleConn": {
+                                "type": "integer",
+                                "minimum": 1,
+                                "default": 90,
+                                "description": "Idle connection timeout in seconds."
+                            }
+                        },
+                        "additionalProperties": false,
+                        "description": "Timeout settings for proxy connections to this peer."
                     }
                 }
             },
@@ -368,4 +445,4 @@
             "description": "A dictionary of remote peers and models they provide. Peers can be another llama-swap or any server that provides the /v1/ generative API endpoints supported by llama-swap."
         }
     }
-}
+}

config.example.yaml

@@ -75,6 +75,11 @@ sendLoadingState: true
 #   all fields except for Id so chat UIs can use the alias equivalent to the original.
 includeAliasesInList: false
 
+# globalTTL: the default TTL in seconds before unloading a model
+# - optional, default: 0 (never automatically unload)
+# - must be >= 0
+globalTTL: 0
+
 # macros: a dictionary of string substitutions
 # - optional, default: empty dictionary
 # - macros are reusable snippets
@@ -180,8 +185,10 @@ models:
     checkEndpoint: /custom-endpoint
 
     # ttl: automatically unload the model after ttl seconds
-    # - optional, default: 0
-    # - ttl values must be a value greater than 0
+    # - optional, default: -1 (use global default)
+    # - ttl values must be a value greater than or equal to 0
+    # - a ttl of -1 will use the global TTL value as the default
+    # - a ttl of 0 will mean never unload
     # - a value of 0 disables automatic unloading of the model
     ttl: 60
 
@@ -277,6 +284,21 @@ models:
     # - optional, default: undefined (use global setting)
     sendLoadingState: false
 
+    # timeouts: configure proxy connection timeouts for this model
+    # - optional, defaults shown below
+    # - useful for models running on slower hardware that need longer timeouts
+    # - connect: TCP connection timeout in seconds
+    # - responseHeader: time to wait for response headers in seconds
+    #   (increasing this helps avoid 502 errors on slow hardware)
+    # - tlsHandshake: TLS handshake timeout in seconds
+    # - idleConn: idle connection timeout in seconds
+    # - set any value to 0 to disable that timeout (not recommended)
+    timeouts:
+      connect: 30
+      responseHeader: 60
+      tlsHandshake: 10
+      idleConn: 90
+
   # Unlisted model example:
   "qwen-unlisted":
     # unlisted: boolean, true or false
@@ -419,6 +441,16 @@ peers:
       - z-ai/glm-4.7
       - moonshotai/kimi-k2-0905
       - minimax/minimax-m2.1
+    # timeouts: configure proxy connection timeouts for this peer
+    # - optional, defaults shown below
+    # - useful when the peer runs on slower hardware
+    # - set any value to 0 to disable that timeout (not recommended)
+    timeouts:
+      connect: 30
+      responseHeader: 60
+      tlsHandshake: 10
+      idleConn: 90
+
     # filters: a dictionary of filter settings for peer requests
     # - optional, default: empty dictionary
     # - same capabilities as model filters (stripParams, setParams)

docker/build-container.sh

@@ -27,7 +27,7 @@ ARCH=$1
 PUSH_IMAGES=${2:-false}
 
 # List of allowed architectures
-ALLOWED_ARCHS=("intel" "vulkan" "musa" "cuda" "cpu" "rocm")
+ALLOWED_ARCHS=("intel" "vulkan" "musa" "cuda" "cuda13" "cpu" "rocm")
 
 # Check if ARCH is in the allowed list
 if [[ ! " ${ALLOWED_ARCHS[@]} " =~ " ${ARCH} " ]]; then

docker/build-image.sh

@@ -0,0 +1,305 @@
+#!/bin/bash
+#
+# Build script for llama-swap-docker with commit hash pinning
+#
+# Usage:
+#   ./build-image.sh --cuda                    # Build CUDA image
+#   ./build-image.sh --vulkan                  # Build Vulkan image
+#   ./build-image.sh --cuda --no-cache         # Build CUDA image without cache
+#   LLAMA_COMMIT_HASH=abc123 ./build-image.sh --cuda      # Override llama.cpp commit
+#   LLAMA_COMMIT_HASH=b8429 ./build-image.sh --vulkan    # Override llama.cpp release tag (vulkan uses prebuilt binaries)
+#   WHISPER_COMMIT_HASH=def456 ./build-image.sh --vulkan  # Override whisper.cpp commit
+#   SD_COMMIT_HASH=ghi789 ./build-image.sh --cuda        # Override stable-diffusion.cpp commit
+#
+# Features:
+#   - Auto-detects latest commit hashes from git repos
+#   - Builds llama-swap from local source code
+#   - Allows environment variable overrides for reproducible builds
+#   - Cache-friendly: changing commit hash busts cache appropriately
+#   - Supports both CUDA and Vulkan backends (requires explicit flag)
+#
+
+set -euo pipefail
+
+# Parse command line arguments
+BACKEND=""
+NO_CACHE=false
+
+if [[ $# -eq 0 ]]; then
+    echo "Error: No backend specified. Please use --cuda or --vulkan."
+    echo ""
+    echo "Usage: ./build-image.sh --cuda|--vulkan [--no-cache]"
+    echo ""
+    echo "Options:"
+    echo "  --cuda      Build CUDA image (NVIDIA GPUs)"
+    echo "  --vulkan    Build Vulkan image (AMD GPUs and compatible hardware)"
+    echo "  --no-cache  Force rebuild without using Docker cache"
+    echo "  --help, -h  Show this help message"
+    echo ""
+    echo "Environment variables:"
+    echo "  DOCKER_IMAGE_TAG     Set custom image tag (default: llama-swap:cuda or llama-swap:vulkan)"
+    echo "  LLAMA_COMMIT_HASH    Override llama.cpp commit hash"
+    echo "  WHISPER_COMMIT_HASH  Override whisper.cpp commit hash"
+    echo "  SD_COMMIT_HASH       Override stable-diffusion.cpp commit hash"
+    exit 1
+fi
+
+for arg in "$@"; do
+    case $arg in
+        --cuda)
+            BACKEND="cuda"
+            ;;
+        --vulkan)
+            BACKEND="vulkan"
+            ;;
+        --no-cache)
+            NO_CACHE=true
+            ;;
+        --help|-h)
+            echo "Usage: ./build-image.sh --cuda|--vulkan [--no-cache]"
+            echo ""
+            echo "Options:"
+            echo "  --cuda      Build CUDA image (NVIDIA GPUs)"
+            echo "  --vulkan    Build Vulkan image (AMD GPUs and compatible hardware)"
+            echo "  --no-cache  Force rebuild without using Docker cache"
+            echo "  --help, -h  Show this help message"
+            echo ""
+            echo "Environment variables:"
+            echo "  DOCKER_IMAGE_TAG     Set custom image tag (default: llama-swap:cuda or llama-swap:vulkan)"
+            echo "  LLAMA_COMMIT_HASH    Override llama.cpp commit hash"
+            echo "  WHISPER_COMMIT_HASH  Override whisper.cpp commit hash"
+            echo "  SD_COMMIT_HASH       Override stable-diffusion.cpp commit hash"
+            exit 0
+            ;;
+    esac
+done
+
+# Validate backend selection
+if [[ -z "$BACKEND" ]]; then
+    echo "Error: No backend specified. Please use --cuda or --vulkan."
+    exit 1
+fi
+
+# Configuration
+if [[ -n "${DOCKER_IMAGE_TAG:-}" ]]; then
+    # User provided a custom tag, use it as-is
+    :
+elif [[ "$BACKEND" == "vulkan" ]]; then
+    DOCKER_IMAGE_TAG="llama-swap:vulkan"
+else
+    DOCKER_IMAGE_TAG="llama-swap:cuda"
+fi
+DOCKER_BUILDKIT="${DOCKER_BUILDKIT:-1}"
+
+# Single unified Dockerfile, backend selected via build arg
+DOCKERFILE="Dockerfile"
+if [[ "$BACKEND" == "vulkan" ]]; then
+    echo "Building for: Vulkan (AMD GPUs and compatible hardware)"
+else
+    echo "Building for: CUDA (NVIDIA GPUs)"
+fi
+
+# Git repository URLs
+LLAMA_REPO="https://github.com/ggml-org/llama.cpp.git"
+WHISPER_REPO="https://github.com/ggml-org/whisper.cpp.git"
+SD_REPO="https://github.com/leejet/stable-diffusion.cpp.git"
+
+# Function to get the latest commit hash from a git repo's default branch
+get_latest_commit() {
+    local repo_url="$1"
+    local branch="${2:-master}"
+
+    # Try to get the latest commit hash for the specified branch
+    git ls-remote --heads "${repo_url}" "${branch}" 2>/dev/null | head -1 | cut -f1
+}
+
+# Function to get the default branch name (master or main)
+get_default_branch() {
+    local repo_url="$1"
+
+    # Check for master first
+    if git ls-remote --heads "${repo_url}" master &>/dev/null; then
+        echo "master"
+    elif git ls-remote --heads "${repo_url}" main &>/dev/null; then
+        echo "main"
+    else
+        echo "master"  # fallback
+    fi
+}
+
+# Function to get the latest release tag from a GitHub repo
+get_latest_release_tag() {
+    local owner_repo="$1"
+    curl -fsSL "https://api.github.com/repos/${owner_repo}/releases/latest" \
+        | grep '"tag_name"' | head -1 | cut -d'"' -f4
+}
+
+echo "=========================================="
+echo "llama-swap-docker Build Script"
+echo "=========================================="
+echo ""
+
+# Determine commit hashes / release tags - use env vars or auto-detect
+# For vulkan builds, llama and sd use GitHub release tags (prebuilt binaries).
+# For cuda builds (or whisper on any backend), use git commit hashes.
+if [[ -n "${LLAMA_COMMIT_HASH:-}" ]]; then
+    LLAMA_HASH="${LLAMA_COMMIT_HASH}"
+    echo "llama.cpp: Using provided version: ${LLAMA_HASH}"
+elif [[ "$BACKEND" == "vulkan" ]]; then
+    LLAMA_HASH=$(get_latest_release_tag "ggml-org/llama.cpp")
+    if [[ -z "${LLAMA_HASH}" ]]; then
+        echo "ERROR: Could not determine latest release tag for llama.cpp" >&2
+        exit 1
+    fi
+    echo "llama.cpp: Auto-detected latest release tag: ${LLAMA_HASH}"
+else
+    LLAMA_BRANCH=$(get_default_branch "${LLAMA_REPO}")
+    LLAMA_HASH=$(get_latest_commit "${LLAMA_REPO}" "${LLAMA_BRANCH}")
+    if [[ -z "${LLAMA_HASH}" ]]; then
+        echo "ERROR: Could not determine latest commit for llama.cpp" >&2
+        exit 1
+    fi
+    echo "llama.cpp: Auto-detected latest commit (${LLAMA_BRANCH}): ${LLAMA_HASH}"
+fi
+
+if [[ -n "${WHISPER_COMMIT_HASH:-}" ]]; then
+    WHISPER_HASH="${WHISPER_COMMIT_HASH}"
+    echo "whisper.cpp: Using provided commit hash: ${WHISPER_HASH}"
+else
+    WHISPER_BRANCH=$(get_default_branch "${WHISPER_REPO}")
+    WHISPER_HASH=$(get_latest_commit "${WHISPER_REPO}" "${WHISPER_BRANCH}")
+    if [[ -z "${WHISPER_HASH}" ]]; then
+        echo "ERROR: Could not determine latest commit for whisper.cpp" >&2
+        exit 1
+    fi
+    echo "whisper.cpp: Auto-detected latest commit (${WHISPER_BRANCH}): ${WHISPER_HASH}"
+fi
+
+if [[ -n "${SD_COMMIT_HASH:-}" ]]; then
+    SD_HASH="${SD_COMMIT_HASH}"
+    echo "stable-diffusion.cpp: Using provided version: ${SD_HASH}"
+elif [[ "$BACKEND" == "vulkan" ]]; then
+    SD_HASH=$(get_latest_release_tag "leejet/stable-diffusion.cpp")
+    if [[ -z "${SD_HASH}" ]]; then
+        echo "ERROR: Could not determine latest release tag for stable-diffusion.cpp" >&2
+        exit 1
+    fi
+    echo "stable-diffusion.cpp: Auto-detected latest release tag: ${SD_HASH}"
+else
+    SD_BRANCH=$(get_default_branch "${SD_REPO}")
+    SD_HASH=$(get_latest_commit "${SD_REPO}" "${SD_BRANCH}")
+    if [[ -z "${SD_HASH}" ]]; then
+        echo "ERROR: Could not determine latest commit for stable-diffusion.cpp" >&2
+        exit 1
+    fi
+    echo "stable-diffusion.cpp: Auto-detected latest commit (${SD_BRANCH}): ${SD_HASH}"
+fi
+
+echo ""
+echo "=========================================="
+echo "Starting Docker build..."
+echo "=========================================="
+echo ""
+
+# Build the Docker image with commit hashes as build args
+# Build context is the repository root (..) so the Dockerfile can access Go source
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+REPO_ROOT="$(cd "${SCRIPT_DIR}/.." && pwd)"
+BUILD_ARGS=(
+    --build-arg "BACKEND=${BACKEND}"
+    --build-arg "LLAMA_COMMIT_HASH=${LLAMA_HASH}"
+    --build-arg "WHISPER_COMMIT_HASH=${WHISPER_HASH}"
+    --build-arg "SD_COMMIT_HASH=${SD_HASH}"
+    -t "${DOCKER_IMAGE_TAG}"
+    -f "${SCRIPT_DIR}/${DOCKERFILE}"
+)
+
+if [[ "$NO_CACHE" == true ]]; then
+    BUILD_ARGS+=(--no-cache)
+    echo "Note: Building without cache"
+fi
+
+# Use docker buildx with a custom builder for parallelism control
+# The legacy DOCKER_BUILDKIT=1 docker build doesn't respect BUILDKIT_MAX_PARALLELISM env var
+# We need to use a custom builder with a buildkitd.toml config file
+BUILDER_NAME="llama-swap-builder"
+
+# Check if our custom builder exists with the right config, create/update if needed
+if ! docker buildx inspect "$BUILDER_NAME" >/dev/null 2>&1; then
+    echo "Creating custom buildx builder with max-parallelism=1..."
+    
+    # Create buildkitd.toml config file
+    cat > buildkitd.toml << 'BUILDKIT_EOF'
+[worker.oci]
+  max-parallelism = 1
+BUILDKIT_EOF
+    
+    # Create the builder with the config
+    docker buildx create --name "$BUILDER_NAME" \
+        --driver docker-container \
+        --buildkitd-config buildkitd.toml \
+        --use
+else
+    # Switch to our builder
+    docker buildx use "$BUILDER_NAME"
+fi
+
+echo "Building with sequential stages (one at a time), each using all CPU cores..."
+echo "Using builder: $BUILDER_NAME"
+
+# Use docker buildx build with --load to load the image into Docker
+# The --builder flag ensures we use our custom builder with max-parallelism=1
+# Build context is the repository root so we can access Go source files
+docker buildx build --builder "$BUILDER_NAME" --load "${BUILD_ARGS[@]}" "${REPO_ROOT}"
+
+echo ""
+echo "=========================================="
+echo "Verifying build artifacts..."
+echo "=========================================="
+echo ""
+
+# Verify all expected binaries exist in the image
+MISSING_BINARIES=()
+
+for binary in llama-server llama-cli whisper-server whisper-cli sd-server sd-cli llama-swap; do
+    if ! docker run --rm "${DOCKER_IMAGE_TAG}" which "${binary}" >/dev/null 2>&1; then
+        MISSING_BINARIES+=("${binary}")
+    fi
+done
+
+if [[ ${#MISSING_BINARIES[@]} -gt 0 ]]; then
+    echo "ERROR: Build succeeded but the following binaries are missing from the image:"
+    for binary in "${MISSING_BINARIES[@]}"; do
+        echo "  - ${binary}"
+    done
+    echo ""
+    echo "This usually indicates a build stage failure. Try running with --no-cache flag:"
+    echo "  ./build-image.sh --vulkan --no-cache"
+    exit 1
+fi
+
+echo "All expected binaries verified: llama-server, llama-cli, whisper-server, whisper-cli, sd-server, sd-cli, llama-swap"
+
+echo ""
+echo "=========================================="
+echo "Build complete!"
+echo "=========================================="
+echo ""
+echo "Image tag: ${DOCKER_IMAGE_TAG}"
+echo ""
+echo "Built with:"
+echo "  llama.cpp:           ${LLAMA_HASH}"
+echo "  whisper.cpp:         ${WHISPER_HASH}"
+echo "  stable-diffusion.cpp: ${SD_HASH}"
+echo "  llama-swap:          $(docker run --rm "${DOCKER_IMAGE_TAG}" cat /versions.txt | grep llama-swap | cut -d' ' -f2-)"
+echo ""
+if [[ "$BACKEND" == "vulkan" ]]; then
+    echo "Run with:"
+    echo "  docker run -it --rm --device /dev/dri:/dev/dri ${DOCKER_IMAGE_TAG}"
+    echo ""
+    echo "Note: For AMD GPUs, you may also need to mount render devices:"
+    echo "  docker run -it --rm --device /dev/dri:/dev/dri --group-add video ${DOCKER_IMAGE_TAG}"
+else
+    echo "Run with:"
+    echo "  docker run -it --rm --gpus all ${DOCKER_IMAGE_TAG}"
+fi

docker/unified/Dockerfile

@@ -0,0 +1,203 @@
+# Unified multi-stage Dockerfile for AI inference tools
+# Supports CUDA and Vulkan backends via BACKEND build arg
+#
+# Usage:
+#   docker buildx build --build-arg BACKEND=cuda -t llama-swap:unified-cuda .
+#   docker buildx build --build-arg BACKEND=vulkan -t llama-swap:unified-vulkan .
+#   docker buildx build --build-arg BACKEND=cuda --build-arg CMAKE_CUDA_ARCHITECTURES="86;89" -t llama-swap:unified-cuda .
+#
+# Each project has its own install script that handles cloning, building,
+# and installing binaries. Build stages are independent for cache efficiency.
+
+ARG BACKEND=cuda
+
+# ── Builder bases ──────────────────────────────────────────────────────
+
+FROM nvidia/cuda:12.9.1-devel-ubuntu24.04 AS builder-base-cuda
+
+ARG CMAKE_CUDA_ARCHITECTURES="60;61;75;86;89"
+ENV DEBIAN_FRONTEND=noninteractive
+ENV CMAKE_CUDA_ARCHITECTURES=${CMAKE_CUDA_ARCHITECTURES}
+ENV CCACHE_DIR=/ccache
+ENV CCACHE_MAXSIZE=2G
+ENV PATH="/usr/lib/ccache:${PATH}"
+
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    build-essential cmake git python3 python3-pip libssl-dev \
+    curl ca-certificates ccache make wget \
+    && rm -rf /var/lib/apt/lists/*
+
+WORKDIR /build
+
+# ──
+
+FROM ubuntu:24.04 AS builder-base-vulkan
+
+ENV DEBIAN_FRONTEND=noninteractive
+ENV CCACHE_DIR=/ccache
+ENV CCACHE_MAXSIZE=2G
+ENV PATH="/usr/lib/ccache:${PATH}"
+
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    build-essential cmake git python3 python3-pip libssl-dev \
+    curl ca-certificates ccache make wget software-properties-common \
+    libvulkan-dev glslang-tools spirv-tools vulkan-validationlayers glslc \
+    && rm -rf /var/lib/apt/lists/*
+
+WORKDIR /build
+
+# ── Select builder base by BACKEND ────────────────────────────────────
+
+FROM builder-base-${BACKEND} AS builder-base
+
+# ── Build whisper.cpp (fastest build, run first) ──────────────────────
+
+FROM builder-base AS whisper-build
+ARG BACKEND=cuda
+ARG WHISPER_COMMIT_HASH=master
+COPY install-whisper.sh /build/
+RUN --mount=type=cache,id=ccache-${BACKEND},target=/ccache \
+    --mount=type=cache,id=whisper-${BACKEND},target=/src/whisper.cpp/build \
+    BACKEND=${BACKEND} bash /build/install-whisper.sh "${WHISPER_COMMIT_HASH}"
+
+# ── Build stable-diffusion.cpp ────────────────────────────────────────
+
+FROM builder-base AS sd-build
+ARG BACKEND=cuda
+ARG SD_COMMIT_HASH=master
+COPY install-sd.sh /build/
+RUN --mount=type=cache,id=ccache-${BACKEND},target=/ccache \
+    --mount=type=cache,id=sd-${BACKEND},target=/src/stable-diffusion.cpp/build \
+    BACKEND=${BACKEND} bash /build/install-sd.sh "${SD_COMMIT_HASH}"
+
+# ── Build llama.cpp (slowest build, run last) ─────────────────────────
+
+FROM builder-base AS llama-build
+ARG BACKEND=cuda
+ARG LLAMA_COMMIT_HASH=master
+COPY install-llama.sh /build/
+RUN --mount=type=cache,id=ccache-${BACKEND},target=/ccache \
+    --mount=type=cache,id=llama-${BACKEND},target=/src/llama.cpp/build \
+    BACKEND=${BACKEND} bash /build/install-llama.sh "${LLAMA_COMMIT_HASH}"
+
+# ── Build ik_llama.cpp (CUDA only) ────────────────────────────────────
+#
+# Two named stages allow ARG BACKEND to select at build time:
+#   - ik-llama-cuda  : real build (from builder-base-cuda)
+#   - ik-llama-vulkan: no-op (empty /install/bin, skips CUDA pull entirely)
+# BuildKit only evaluates the selected branch, so vulkan builds never
+# pull nvidia/cuda:*-devel or compile ik_llama.cpp.
+
+FROM builder-base-vulkan AS ik-llama-vulkan
+RUN mkdir -p /install/bin
+
+FROM builder-base-cuda AS ik-llama-cuda
+ARG IK_LLAMA_COMMIT_HASH=main
+COPY install-ik-llama.sh /build/
+RUN --mount=type=cache,id=ccache-cuda,target=/ccache \
+    --mount=type=cache,id=ik-llama-cuda,target=/src/ik_llama.cpp/build \
+    bash /build/install-ik-llama.sh "${IK_LLAMA_COMMIT_HASH}"
+
+ARG BACKEND=cuda
+FROM ik-llama-${BACKEND} AS ik-llama-build
+
+# ── Download llama-swap release binary ────────────────────────────────
+
+FROM builder-base AS llama-swap-download
+ARG LS_VERSION=latest
+COPY install-llama-swap.sh /build/
+RUN bash /build/install-llama-swap.sh "${LS_VERSION}"
+
+# ── Runtime bases ─────────────────────────────────────────────────────
+
+FROM nvidia/cuda:12.9.1-runtime-ubuntu24.04 AS runtime-cuda
+
+ENV DEBIAN_FRONTEND=noninteractive
+ENV LD_LIBRARY_PATH="/usr/local/cuda/lib64:${LD_LIBRARY_PATH}"
+ENV PATH="/usr/local/bin:${PATH}"
+
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    libgomp1 python3 curl ca-certificates \
+    && rm -rf /var/lib/apt/lists/*
+
+# CUDA stub drivers for container compatibility
+COPY --from=builder-base-cuda /usr/local/cuda/lib64/stubs/libcuda.so /usr/local/cuda/lib64/stubs/libcuda.so
+COPY --from=builder-base-cuda /usr/local/cuda/lib64/stubs/libcuda.so /usr/local/cuda/lib64/stubs/libcuda.so.1
+
+# ──
+
+FROM ubuntu:24.04 AS runtime-vulkan
+
+ENV DEBIAN_FRONTEND=noninteractive
+ENV PATH="/usr/local/bin:${PATH}"
+
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    libgomp1 libvulkan1 mesa-vulkan-drivers \
+    python3 curl ca-certificates \
+    && rm -rf /var/lib/apt/lists/*
+
+# ── Select runtime base by BACKEND ────────────────────────────────────
+
+FROM runtime-${BACKEND} AS runtime
+
+ARG BACKEND=cuda
+ARG LLAMA_COMMIT_HASH=unknown
+ARG WHISPER_COMMIT_HASH=unknown
+ARG SD_COMMIT_HASH=unknown
+ARG IK_LLAMA_COMMIT_HASH=unknown
+ARG RUN_UID=0
+
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    python3-numpy python3-sentencepiece \
+    && rm -rf /var/lib/apt/lists/*
+
+# Create non-root user when RUN_UID != 0
+RUN if [ "$RUN_UID" != "0" ]; then \
+      groupadd --system --gid $RUN_UID llama-swap && \
+      useradd --system --uid $RUN_UID --gid $RUN_UID \
+        --home /app --shell /sbin/nologin llama-swap; \
+    fi && \
+    mkdir -p /etc/llama-swap/config && \
+    chown -R ${RUN_UID}:${RUN_UID} /etc/llama-swap
+
+WORKDIR /app
+
+# Copy whisper.cpp binaries and libraries
+COPY --from=whisper-build /install/bin/whisper-server /usr/local/bin/
+COPY --from=whisper-build /install/bin/whisper-cli /usr/local/bin/
+COPY --from=whisper-build /install/lib/ /usr/local/lib/
+
+# Copy stable-diffusion.cpp binaries and libraries
+COPY --from=sd-build /install/bin/sd-server /usr/local/bin/
+COPY --from=sd-build /install/bin/sd-cli /usr/local/bin/
+COPY --from=sd-build /install/lib/ /usr/local/lib/
+
+# Copy llama.cpp binaries (statically linked)
+COPY --from=llama-build /install/bin/llama-server /usr/local/bin/
+COPY --from=llama-build /install/bin/llama-cli /usr/local/bin/
+
+# Copy ik-llama-server (CUDA only; empty copy for vulkan)
+COPY --from=ik-llama-build /install/bin/ /usr/local/bin/
+
+# Copy llama-swap binary
+COPY --from=llama-swap-download /install/bin/llama-swap /usr/local/bin/
+COPY --from=llama-swap-download /install/llama-swap-version /tmp/
+
+RUN ldconfig
+
+COPY config.example.yaml /etc/llama-swap/config/config.yaml
+
+# Version tracking
+RUN echo "llama.cpp: ${LLAMA_COMMIT_HASH}" > /versions.txt && \
+    echo "whisper.cpp: ${WHISPER_COMMIT_HASH}" >> /versions.txt && \
+    echo "stable-diffusion.cpp: ${SD_COMMIT_HASH}" >> /versions.txt && \
+    echo "ik_llama.cpp: ${IK_LLAMA_COMMIT_HASH}" >> /versions.txt && \
+    echo "llama-swap: $(cat /tmp/llama-swap-version)" >> /versions.txt && \
+    echo "backend: ${BACKEND}" >> /versions.txt && \
+    echo "build_timestamp: $(date -u +%Y-%m-%dT%H:%M:%SZ)" >> /versions.txt
+
+RUN mkdir -p /models && chown ${RUN_UID}:${RUN_UID} /models
+WORKDIR /models
+USER ${RUN_UID}
+ENTRYPOINT ["llama-swap"]
+CMD ["-config", "/etc/llama-swap/config/config.yaml", "-listen", "0.0.0.0:8080"]

docker/unified/README.md

@@ -0,0 +1,8 @@
+# Unified Docker Container
+
+These scripts create a custom llama-swap container that contains:
+
+- llama-server for LLMs, rerank and embedding model support
+- sd-server (stable-diffusion.cpp) for image generation
+- whisper.cpp for ASR
+

docker/unified/build-image.sh

@@ -0,0 +1,283 @@
+#!/bin/bash
+#
+# Build script for unified container with version pinning
+#
+# Usage:
+#   ./build-image.sh --cuda                              # Build CUDA image
+#   ./build-image.sh --vulkan                            # Build Vulkan image
+#   ./build-image.sh --cuda --no-cache                   # Build without cache
+#   LLAMA_REF=b1234 ./build-image.sh --vulkan            # Pin llama.cpp to a commit hash
+#   LLAMA_REF=v1.2.3 ./build-image.sh --cuda             # Pin llama.cpp to a tag
+#   WHISPER_REF=v1.0.0 ./build-image.sh --vulkan         # Pin whisper.cpp to a tag
+#   SD_REF=master ./build-image.sh --cuda                # Pin stable-diffusion.cpp to a branch
+#   LS_VERSION=170 ./build-image.sh --cuda               # Override llama-swap version
+#   IK_LLAMA_REF=main ./build-image.sh --cuda            # Pin ik_llama.cpp to main branch (CUDA only)
+#
+
+set -euo pipefail
+
+BACKEND=""
+NO_CACHE=false
+
+for arg in "$@"; do
+    case $arg in
+        --cuda)
+            BACKEND="cuda"
+            ;;
+        --vulkan)
+            BACKEND="vulkan"
+            ;;
+        --no-cache)
+            NO_CACHE=true
+            ;;
+        --help|-h)
+            echo "Usage: ./build-image.sh --cuda|--vulkan [--no-cache]"
+            echo ""
+            echo "Options:"
+            echo "  --cuda      Build CUDA image (NVIDIA GPUs)"
+            echo "  --vulkan    Build Vulkan image (AMD GPUs and compatible hardware)"
+            echo "  --no-cache  Force rebuild without using Docker cache"
+            echo "  --help, -h  Show this help message"
+            echo ""
+            echo "Environment variables:"
+            echo "  DOCKER_IMAGE_TAG     Set custom image tag (default: llama-swap:unified-cuda or llama-swap:unified-vulkan)"
+            echo "  LLAMA_REF            Pin llama.cpp to a commit, tag, or branch"
+            echo "  WHISPER_REF          Pin whisper.cpp to a commit, tag, or branch"
+            echo "  SD_REF               Pin stable-diffusion.cpp to a commit, tag, or branch"
+            echo "  IK_LLAMA_REF         Pin ik_llama.cpp to a commit, tag, or branch (CUDA only)"
+            echo "  LS_VERSION           Override llama-swap version (e.g., '170' or 'latest')"
+            exit 0
+            ;;
+    esac
+done
+
+if [[ -z "$BACKEND" ]]; then
+    echo "Error: No backend specified. Please use --cuda or --vulkan."
+    echo ""
+    echo "Usage: ./build-image.sh --cuda|--vulkan [--no-cache]"
+    exit 1
+fi
+
+DOCKER_IMAGE_TAG="${DOCKER_IMAGE_TAG:-llama-swap:unified-${BACKEND}}"
+
+# Git repository URLs
+LLAMA_REPO="https://github.com/ggml-org/llama.cpp.git"
+WHISPER_REPO="https://github.com/ggml-org/whisper.cpp.git"
+SD_REPO="https://github.com/leejet/stable-diffusion.cpp.git"
+LLAMA_SWAP_REPO="https://github.com/mostlygeek/llama-swap.git"
+IK_LLAMA_REPO="https://github.com/ikawrakow/ik_llama.cpp.git"
+
+# Resolve a git ref (commit hash, tag, or branch) to a full commit hash.
+# Requires only: git, network access to the remote.
+resolve_ref() {
+    local repo_url="$1"
+    local ref="$2"
+
+    # Full 40-char SHA — use as-is
+    if [[ "${ref}" =~ ^[0-9a-f]{40}$ ]]; then
+        echo "${ref}"
+        return
+    fi
+
+    # Try tag then branch (exact match)
+    local hash
+    hash=$(git ls-remote "${repo_url}" "refs/tags/${ref}" "refs/heads/${ref}" 2>/dev/null | head -1 | cut -f1)
+    if [[ -n "${hash}" ]]; then
+        echo "${hash}"
+        return
+    fi
+
+    # Short hash (7+ chars): scan all refs for a SHA with this prefix
+    if [[ "${ref}" =~ ^[0-9a-f]{7,}$ ]]; then
+        hash=$(git ls-remote "${repo_url}" 2>/dev/null | grep "^${ref}" | head -1 | cut -f1)
+        if [[ -n "${hash}" ]]; then
+            echo "${hash}"
+            return
+        fi
+    fi
+
+    echo "ERROR: Could not resolve ref '${ref}' for ${repo_url}" >&2
+    if [[ "${ref}" =~ ^[0-9a-f]+$ && ${#ref} -lt 7 ]]; then
+        echo "  Short hashes must be at least 7 characters (got ${#ref})." >&2
+    else
+        echo "  Tried: tag, branch, git ls-remote prefix match" >&2
+    fi
+    echo "  Use a full 40-char SHA, a tag name, a branch name, or a 7+ char short hash." >&2
+    return 1
+}
+
+# Resolve HEAD of a repo without needing to know the default branch name.
+get_latest_hash() {
+    git ls-remote "${1}" HEAD 2>/dev/null | head -1 | cut -f1
+}
+
+echo "=========================================="
+echo "llama-swap Unified Build (${BACKEND})"
+echo "=========================================="
+echo ""
+
+# Resolve llama.cpp ref
+if [[ -n "${LLAMA_REF:-}" ]]; then
+    LLAMA_HASH=$(resolve_ref "${LLAMA_REPO}" "${LLAMA_REF}") || exit 1
+    echo "llama.cpp: ${LLAMA_REF} -> ${LLAMA_HASH}"
+else
+    LLAMA_HASH=$(get_latest_hash "${LLAMA_REPO}")
+    if [[ -z "${LLAMA_HASH}" ]]; then
+        echo "ERROR: Could not determine latest commit for llama.cpp" >&2
+        exit 1
+    fi
+    echo "llama.cpp: latest HEAD: ${LLAMA_HASH}"
+fi
+
+# Resolve whisper.cpp ref
+if [[ -n "${WHISPER_REF:-}" ]]; then
+    WHISPER_HASH=$(resolve_ref "${WHISPER_REPO}" "${WHISPER_REF}") || exit 1
+    echo "whisper.cpp: ${WHISPER_REF} -> ${WHISPER_HASH}"
+else
+    WHISPER_HASH=$(get_latest_hash "${WHISPER_REPO}")
+    if [[ -z "${WHISPER_HASH}" ]]; then
+        echo "ERROR: Could not determine latest commit for whisper.cpp" >&2
+        exit 1
+    fi
+    echo "whisper.cpp: latest HEAD: ${WHISPER_HASH}"
+fi
+
+# Resolve stable-diffusion.cpp ref
+if [[ -n "${SD_REF:-}" ]]; then
+    SD_HASH=$(resolve_ref "${SD_REPO}" "${SD_REF}") || exit 1
+    echo "stable-diffusion.cpp: ${SD_REF} -> ${SD_HASH}"
+else
+    SD_HASH=$(get_latest_hash "${SD_REPO}")
+    if [[ -z "${SD_HASH}" ]]; then
+        echo "ERROR: Could not determine latest commit for stable-diffusion.cpp" >&2
+        exit 1
+    fi
+    echo "stable-diffusion.cpp: latest HEAD: ${SD_HASH}"
+fi
+
+# Resolve ik_llama.cpp ref (CUDA only)
+if [[ "$BACKEND" == "cuda" ]]; then
+    if [[ -n "${IK_LLAMA_REF:-}" ]]; then
+        IK_LLAMA_HASH=$(resolve_ref "${IK_LLAMA_REPO}" "${IK_LLAMA_REF}") || exit 1
+        echo "ik_llama.cpp: ${IK_LLAMA_REF} -> ${IK_LLAMA_HASH}"
+    else
+        IK_LLAMA_HASH=$(get_latest_hash "${IK_LLAMA_REPO}")
+        if [[ -z "${IK_LLAMA_HASH}" ]]; then
+            echo "ERROR: Could not determine latest commit for ik_llama.cpp" >&2
+            exit 1
+        fi
+        echo "ik_llama.cpp: latest HEAD: ${IK_LLAMA_HASH}"
+    fi
+else
+    IK_LLAMA_HASH="n/a"
+    echo "ik_llama.cpp: skipped (vulkan build)"
+fi
+
+# Resolve llama-swap ref
+if [[ -n "${LS_VERSION:-}" ]]; then
+    LS_HASH=$(resolve_ref "${LLAMA_SWAP_REPO}" "${LS_VERSION}") || exit 1
+    echo "llama-swap: ${LS_VERSION} -> ${LS_HASH}"
+else
+    LS_HASH=$(get_latest_hash "${LLAMA_SWAP_REPO}")
+    if [[ -z "${LS_HASH}" ]]; then
+        echo "ERROR: Could not determine latest commit for llama-swap" >&2
+        exit 1
+    fi
+    echo "llama-swap: latest HEAD: ${LS_HASH}"
+fi
+
+echo ""
+echo "=========================================="
+echo "Starting Docker build..."
+echo "=========================================="
+echo ""
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+
+BUILD_ARGS=(
+    --build-arg "BACKEND=${BACKEND}"
+    --build-arg "LLAMA_COMMIT_HASH=${LLAMA_HASH}"
+    --build-arg "WHISPER_COMMIT_HASH=${WHISPER_HASH}"
+    --build-arg "SD_COMMIT_HASH=${SD_HASH}"
+    --build-arg "IK_LLAMA_COMMIT_HASH=${IK_LLAMA_HASH}"
+    --build-arg "LS_VERSION=${LS_HASH}"
+    --build-arg "RUN_UID=${RUN_UID:-0}"
+    -t "${DOCKER_IMAGE_TAG}"
+    -f "${SCRIPT_DIR}/Dockerfile"
+)
+
+if [[ "$NO_CACHE" == true ]]; then
+    BUILD_ARGS+=(--no-cache)
+    echo "Note: Building without cache"
+elif [[ "${GITHUB_ACTIONS:-}" == "true" && "${ACT:-}" != "true" ]]; then
+    CACHE_REF="ghcr.io/mostlygeek/llama-swap:unified-${BACKEND}-cache"
+    BUILD_ARGS+=(
+        --cache-from "type=registry,ref=${CACHE_REF}"
+        --cache-to "type=registry,ref=${CACHE_REF},mode=max"
+    )
+    echo "Note: Using registry cache (${CACHE_REF})"
+fi
+
+DOCKER_BUILDKIT=1 docker buildx build --load "${BUILD_ARGS[@]}" "${SCRIPT_DIR}"
+
+echo ""
+echo "=========================================="
+echo "Verifying build artifacts..."
+echo "=========================================="
+echo ""
+
+EXPECTED_BINARIES=(llama-server llama-cli whisper-server whisper-cli sd-server sd-cli llama-swap)
+if [[ "$BACKEND" == "cuda" ]]; then
+    EXPECTED_BINARIES+=(ik-llama-server)
+fi
+
+MISSING_BINARIES=()
+for binary in "${EXPECTED_BINARIES[@]}"; do
+    if ! docker run --rm --entrypoint which "${DOCKER_IMAGE_TAG}" "${binary}" >/dev/null 2>&1; then
+        MISSING_BINARIES+=("${binary}")
+    fi
+done
+
+if [[ ${#MISSING_BINARIES[@]} -gt 0 ]]; then
+    echo "ERROR: Build succeeded but the following binaries are missing:"
+    for binary in "${MISSING_BINARIES[@]}"; do
+        echo "  - ${binary}"
+    done
+    echo ""
+    echo "Try running with --no-cache flag:"
+    echo "  ./build-image.sh --${BACKEND} --no-cache"
+    exit 1
+fi
+
+VERIFIED_LIST="llama-server, llama-cli, whisper-server, whisper-cli, sd-server, sd-cli, llama-swap"
+if [[ "$BACKEND" == "cuda" ]]; then
+    VERIFIED_LIST="${VERIFIED_LIST}, ik-llama-server"
+fi
+echo "All expected binaries verified: ${VERIFIED_LIST}"
+
+echo ""
+echo "=========================================="
+echo "Build complete!"
+echo "=========================================="
+echo ""
+echo "Image tag: ${DOCKER_IMAGE_TAG}"
+echo ""
+echo "Built with:"
+echo "  llama.cpp:            ${LLAMA_HASH}"
+echo "  whisper.cpp:          ${WHISPER_HASH}"
+echo "  stable-diffusion.cpp: ${SD_HASH}"
+if [[ "$BACKEND" == "cuda" ]]; then
+    echo "  ik_llama.cpp:         ${IK_LLAMA_HASH}"
+fi
+echo "  llama-swap:           $(docker run --rm --entrypoint cat "${DOCKER_IMAGE_TAG}" /versions.txt | grep llama-swap | cut -d' ' -f2-)"
+echo ""
+if [[ "$BACKEND" == "vulkan" ]]; then
+    echo "Run with:"
+    echo "  docker run -it --rm --device /dev/dri:/dev/dri ${DOCKER_IMAGE_TAG}"
+    echo ""
+    echo "Note: For AMD GPUs, you may also need:"
+    echo "  docker run -it --rm --device /dev/dri:/dev/dri --group-add video ${DOCKER_IMAGE_TAG}"
+else
+    echo "Run with:"
+    echo "  docker run -it --rm --gpus all ${DOCKER_IMAGE_TAG}"
+fi

docker/unified/config.example.yaml

@@ -0,0 +1,33 @@
+# placeholder example configuration
+healthCheckTimeout: 300
+logRequests: true
+
+models:
+  "llama":
+    cmd: >
+      llama-server
+      -hf bartowski/Qwen2.5-0.5B-Instruct-GGUF:Q4_K_M
+      --port ${PORT}
+
+  "whisper":
+    checkEndpoint: /v1/audio/transcriptions/
+    cmd: >
+      whisper-server
+      --port ${PORT}
+      --m /models/whisper.bin
+      --flash-attn
+      --request-path /v1/audio/transcriptions --inference-path ""
+
+  "image":
+    checkEndpoint: /
+    cmd: |
+      /app/sd-server
+      --listen-port 9999
+      --diffusion-fa
+      --diffusion-model /models/z_image_turbo-Q8_0.gguf
+      --vae /models/ae.safetensors
+      --llm /models/qwen3-4b-instruct-2507-q8_0.gguf
+      --offload-to-cpu
+      --cfg-scale 1.0
+      --height 512 --width 512
+      --steps 8

docker/unified/install-ik-llama.sh

@@ -0,0 +1,48 @@
+#!/bin/bash
+# Install ik_llama.cpp - clone, build, and install binaries
+# Usage: ./install-ik-llama.sh <commit_hash>
+# Note: CUDA only; always built against builder-base-cuda
+set -e
+
+COMMIT_HASH="${1:-main}"
+
+mkdir -p /install/bin
+
+# Clone and checkout (init-based so cache-mounted build dir doesn't break clone)
+echo "=== Cloning ik_llama.cpp at ${COMMIT_HASH} ==="
+mkdir -p /src/ik_llama.cpp
+cd /src/ik_llama.cpp
+if [ ! -d .git ]; then
+    git init
+    git remote add origin https://github.com/ikawrakow/ik_llama.cpp.git
+fi
+git fetch --depth=1 origin "${COMMIT_HASH}"
+git checkout FETCH_HEAD
+
+CMAKE_FLAGS=(
+    -DGGML_NATIVE=OFF
+    -DBUILD_SHARED_LIBS=OFF
+    -DCMAKE_BUILD_TYPE=Release
+    -DCMAKE_C_COMPILER_LAUNCHER=ccache
+    -DCMAKE_CXX_COMPILER_LAUNCHER=ccache
+    -DGGML_CUDA=ON
+    "-DCMAKE_CUDA_ARCHITECTURES=${CMAKE_CUDA_ARCHITECTURES:?CMAKE_CUDA_ARCHITECTURES must be set}"
+    "-DCMAKE_CUDA_FLAGS=-allow-unsupported-compiler"
+    "-DCMAKE_EXE_LINKER_FLAGS=-Wl,-rpath-link,/usr/local/cuda/lib64/stubs -lcuda -Wl,--allow-shlib-undefined"
+)
+
+rm -rf build/CMakeCache.txt build/CMakeFiles 2>/dev/null || true
+
+echo "=== Building ik_llama.cpp ==="
+cmake -B build "${CMAKE_FLAGS[@]}"
+cmake --build build --config Release -j"$(nproc)" --target llama-server
+
+if [ ! -f "build/bin/llama-server" ]; then
+    echo "FATAL: llama-server not found in build/bin/" >&2
+    exit 1
+fi
+
+# Install as ik-llama-server to avoid collision with llama.cpp's llama-server
+cp "build/bin/llama-server" "/install/bin/ik-llama-server"
+echo "=== ik_llama.cpp build complete ==="
+ls -la /install/bin/

docker/unified/install-llama-swap.sh

@@ -0,0 +1,59 @@
+#!/bin/bash
+# Install llama-swap - download latest release binary from GitHub
+# Usage: ./install-llama-swap.sh [version]
+#   version: release version number (e.g., "170") or "latest" (default)
+set -e
+
+VERSION="${1:-latest}"
+REPO="mostlygeek/llama-swap"
+
+mkdir -p /install/bin
+
+# If a full commit hash is given, find the release tag that points to it
+if echo "${VERSION}" | grep -qE '^[0-9a-f]{40}$'; then
+    echo "=== Resolving commit ${VERSION:0:7} to release tag ==="
+    TAG=$(git ls-remote --tags "https://github.com/${REPO}.git" 2>/dev/null \
+        | grep "^${VERSION}" | sed 's|.*refs/tags/||' | grep -v '\^{}' | head -1)
+    if [ -n "${TAG}" ]; then
+        echo "Resolved to tag: ${TAG}"
+        VERSION="${TAG#v}"
+    else
+        echo "No release tag found for commit ${VERSION:0:7}, using latest"
+        VERSION="latest"
+    fi
+fi
+
+# Strip leading 'v' prefix so both "198" and "v198" work
+VERSION="${VERSION#v}"
+
+# Resolve "latest" to actual version number
+if [ "$VERSION" = "latest" ]; then
+    echo "=== Resolving latest llama-swap release ==="
+    VERSION=$(curl -fsSL "https://api.github.com/repos/${REPO}/releases/latest" \
+        | grep '"tag_name"' | head -1 | cut -d'"' -f4 | sed 's/^v//')
+    if [ -z "$VERSION" ]; then
+        echo "FATAL: Could not determine latest release version" >&2
+        exit 1
+    fi
+    echo "Latest version: ${VERSION}"
+fi
+
+# Download and extract
+URL="https://github.com/${REPO}/releases/download/v${VERSION}/llama-swap_${VERSION}_linux_amd64.tar.gz"
+echo "=== Downloading llama-swap v${VERSION} ==="
+echo "URL: $URL"
+curl -fSL -o /tmp/llama-swap.tar.gz "$URL"
+tar -xzf /tmp/llama-swap.tar.gz -C /install/bin/
+rm /tmp/llama-swap.tar.gz
+
+# Validate
+if [ ! -x "/install/bin/llama-swap" ]; then
+    echo "FATAL: llama-swap binary not found or not executable" >&2
+    ls -la /install/bin/ >&2
+    exit 1
+fi
+
+echo "$VERSION" > /install/llama-swap-version
+
+echo "=== llama-swap v${VERSION} installed ==="
+ls -la /install/bin/llama-swap

docker/unified/install-llama.sh

@@ -0,0 +1,63 @@
+#!/bin/bash
+# Install llama.cpp - clone, build, and install binaries
+# Usage: BACKEND=cuda|vulkan ./install-llama.sh <commit_hash>
+set -e
+
+COMMIT_HASH="${1:-master}"
+BACKEND="${BACKEND:-cuda}"
+
+mkdir -p /install/bin
+
+# Clone and checkout (init-based so cache-mounted /src/llama.cpp/build dir doesn't break clone)
+echo "=== Cloning llama.cpp at ${COMMIT_HASH} ==="
+mkdir -p /src/llama.cpp
+cd /src/llama.cpp
+if [ ! -d .git ]; then
+    git init
+    git remote add origin https://github.com/ggml-org/llama.cpp.git
+fi
+git fetch --depth=1 origin "${COMMIT_HASH}"
+git checkout FETCH_HEAD
+
+# Common cmake flags
+CMAKE_FLAGS=(
+    -DGGML_NATIVE=OFF
+    -DBUILD_SHARED_LIBS=OFF
+    -DCMAKE_BUILD_TYPE=Release
+    -DCMAKE_C_COMPILER_LAUNCHER=ccache
+    -DCMAKE_CXX_COMPILER_LAUNCHER=ccache
+    -DLLAMA_BUILD_TESTS=OFF
+)
+
+if [ "$BACKEND" = "cuda" ]; then
+    CMAKE_FLAGS+=(
+        -DGGML_CUDA=ON
+        -DGGML_VULKAN=OFF
+        "-DCMAKE_CUDA_ARCHITECTURES=${CMAKE_CUDA_ARCHITECTURES:?CMAKE_CUDA_ARCHITECTURES must be set}"
+        "-DCMAKE_CUDA_FLAGS=-allow-unsupported-compiler"
+        "-DCMAKE_EXE_LINKER_FLAGS=-Wl,-rpath-link,/usr/local/cuda/lib64/stubs -lcuda"
+    )
+elif [ "$BACKEND" = "vulkan" ]; then
+    CMAKE_FLAGS+=(
+        -DGGML_CUDA=OFF
+        -DGGML_VULKAN=ON
+    )
+fi
+
+TARGETS=(llama-cli llama-server)
+
+rm -rf build/CMakeCache.txt build/CMakeFiles 2>/dev/null || true
+
+echo "=== Building llama.cpp for ${BACKEND} ==="
+cmake -B build "${CMAKE_FLAGS[@]}"
+cmake --build build --config Release -j"$(nproc)" --target "${TARGETS[@]}"
+
+for bin in "${TARGETS[@]}"; do
+    if [ ! -f "build/bin/$bin" ]; then
+        echo "FATAL: $bin not found in build/bin/" >&2
+        exit 1
+    fi
+    cp "build/bin/$bin" "/install/bin/"
+done
+echo "=== llama.cpp build complete ==="
+ls -la /install/bin/

docker/unified/install-sd.sh

@@ -0,0 +1,68 @@
+#!/bin/bash
+# Install stable-diffusion.cpp - clone, build, and install binaries and library
+# Usage: BACKEND=cuda|vulkan ./install-sd.sh <commit_hash>
+set -e
+
+COMMIT_HASH="${1:-master}"
+BACKEND="${BACKEND:-cuda}"
+
+mkdir -p /install/bin /install/lib
+
+# Clone and checkout (init-based so cache-mounted /src/stable-diffusion.cpp/build dir doesn't break clone)
+echo "=== Cloning stable-diffusion.cpp at ${COMMIT_HASH} ==="
+mkdir -p /src/stable-diffusion.cpp
+cd /src/stable-diffusion.cpp
+if [ ! -d .git ]; then
+    git init
+    git remote add origin https://github.com/leejet/stable-diffusion.cpp.git
+fi
+git fetch --depth=1 origin "${COMMIT_HASH}"
+git checkout FETCH_HEAD
+git submodule update --init --recursive --depth=1
+
+# Common cmake flags
+CMAKE_FLAGS=(
+    -DGGML_NATIVE=OFF
+    -DCMAKE_BUILD_TYPE=Release
+    -DCMAKE_C_COMPILER_LAUNCHER=ccache
+    -DCMAKE_CXX_COMPILER_LAUNCHER=ccache
+    -DSD_BUILD_EXAMPLES=ON
+)
+
+if [ "$BACKEND" = "cuda" ]; then
+    CMAKE_FLAGS+=(
+        -DGGML_CUDA=ON
+        -DGGML_VULKAN=OFF
+        "-DCMAKE_CUDA_ARCHITECTURES=${CMAKE_CUDA_ARCHITECTURES:?CMAKE_CUDA_ARCHITECTURES must be set}"
+        "-DCMAKE_CUDA_FLAGS=-allow-unsupported-compiler"
+        "-DCMAKE_EXE_LINKER_FLAGS=-Wl,-rpath-link,/usr/local/cuda/lib64/stubs -lcuda"
+        "-DCMAKE_SHARED_LINKER_FLAGS=-Wl,-rpath-link,/usr/local/cuda/lib64/stubs -lcuda"
+        -DSD_CUDA=ON
+    )
+elif [ "$BACKEND" = "vulkan" ]; then
+    CMAKE_FLAGS+=(
+        -DGGML_CUDA=OFF
+        -DGGML_VULKAN=ON
+        -DSD_VULKAN=ON
+    )
+fi
+
+TARGETS=(stable-diffusion sd-cli sd-server)
+
+rm -rf build/CMakeCache.txt build/CMakeFiles 2>/dev/null || true
+
+echo "=== Building stable-diffusion.cpp for ${BACKEND} ==="
+cmake -B build "${CMAKE_FLAGS[@]}"
+cmake --build build --config Release -j"$(nproc)" --target "${TARGETS[@]}"
+
+for bin in sd-cli sd-server; do
+    if [ ! -f "build/bin/$bin" ]; then
+        echo "FATAL: $bin not found in build/bin/" >&2
+        exit 1
+    fi
+    cp "build/bin/$bin" "/install/bin/"
+done
+find build -name "*.so*" -type f -exec cp {} /install/lib/ \;
+
+echo "=== stable-diffusion.cpp build complete ==="
+ls -la /install/bin/ /install/lib/

docker/unified/install-whisper.sh

@@ -0,0 +1,64 @@
+#!/bin/bash
+# Install whisper.cpp - clone, build, and install binaries
+# Usage: BACKEND=cuda|vulkan ./install-whisper.sh <commit_hash>
+set -e
+
+COMMIT_HASH="${1:-master}"
+BACKEND="${BACKEND:-cuda}"
+
+mkdir -p /install/bin /install/lib
+
+# Clone and checkout (init-based so cache-mounted /src/whisper.cpp/build dir doesn't break clone)
+echo "=== Cloning whisper.cpp at ${COMMIT_HASH} ==="
+mkdir -p /src/whisper.cpp
+cd /src/whisper.cpp
+if [ ! -d .git ]; then
+    git init
+    git remote add origin https://github.com/ggml-org/whisper.cpp.git
+fi
+git fetch --depth=1 origin "${COMMIT_HASH}"
+git checkout FETCH_HEAD
+
+# Common cmake flags
+CMAKE_FLAGS=(
+    -DGGML_NATIVE=OFF
+    -DCMAKE_BUILD_TYPE=Release
+    -DCMAKE_C_COMPILER_LAUNCHER=ccache
+    -DCMAKE_CXX_COMPILER_LAUNCHER=ccache
+)
+
+if [ "$BACKEND" = "cuda" ]; then
+    CMAKE_FLAGS+=(
+        -DGGML_CUDA=ON
+        -DGGML_VULKAN=OFF
+        "-DCMAKE_CUDA_ARCHITECTURES=${CMAKE_CUDA_ARCHITECTURES:?CMAKE_CUDA_ARCHITECTURES must be set}"
+        "-DCMAKE_CUDA_FLAGS=-allow-unsupported-compiler"
+        "-DCMAKE_EXE_LINKER_FLAGS=-Wl,-rpath-link,/usr/local/cuda/lib64/stubs -lcuda"
+        "-DCMAKE_SHARED_LINKER_FLAGS=-Wl,-rpath-link,/usr/local/cuda/lib64/stubs -lcuda"
+    )
+elif [ "$BACKEND" = "vulkan" ]; then
+    CMAKE_FLAGS+=(
+        -DGGML_CUDA=OFF
+        -DGGML_VULKAN=ON
+    )
+fi
+
+TARGETS=(whisper-cli whisper-server)
+
+rm -rf build/CMakeCache.txt build/CMakeFiles 2>/dev/null || true
+
+echo "=== Building whisper.cpp for ${BACKEND} ==="
+cmake -B build "${CMAKE_FLAGS[@]}"
+cmake --build build --config Release -j"$(nproc)" --target "${TARGETS[@]}"
+
+for bin in "${TARGETS[@]}"; do
+    if [ ! -f "build/bin/$bin" ]; then
+        echo "FATAL: $bin not found in build/bin/" >&2
+        exit 1
+    fi
+    cp "build/bin/$bin" "/install/bin/"
+done
+find build -name "*.so*" -type f -exec cp {} /install/lib/ \;
+
+echo "=== whisper.cpp build complete ==="
+ls -la /install/bin/

docs/configuration.md

@@ -319,6 +319,29 @@ models:
     # - recommended to be omitted and the default used
     concurrencyLimit: 0
 
+    # timeouts: configure proxy connection timeouts for this model
+    # - optional, defaults shown below
+    # - useful for models on slower hardware that need longer timeouts
+    # - increase responseHeader to avoid "timeout awaiting response headers" errors
+    # - set any value to 0 to disable that timeout (not recommended)
+    timeouts:
+      # connect: TCP connection timeout in seconds
+      # - default: 30
+      connect: 30
+
+      # responseHeader: time to wait for response headers in seconds
+      # - default: 60
+      # - for slow image generation or large models, consider increasing to 300+ seconds
+      responseHeader: 60
+
+      # tlsHandshake: TLS handshake timeout in seconds
+      # - default: 10
+      tlsHandshake: 10
+
+      # idleConn: idle connection timeout in seconds
+      # - default: 90
+      idleConn: 90
+
     # sendLoadingState: overrides the global sendLoadingState setting for this model
     # - optional, default: undefined (use global setting)
     sendLoadingState: false
@@ -444,6 +467,17 @@ peers:
     # - required
     # - requested path to llama-swap will be appended to the end of the proxy value
     proxy: http://192.168.1.23
+
+    # timeouts: configure proxy connection timeouts for this peer
+    # - optional, defaults shown below
+    # - useful when the peer runs on slower hardware
+    # - set any value to 0 to disable that timeout (not recommended)
+    timeouts:
+      connect: 30
+      responseHeader: 60
+      tlsHandshake: 10
+      idleConn: 90
+
     # models: a list of models served by the peer
     # - required
     models:

go.mod

@@ -1,6 +1,6 @@
 module github.com/mostlygeek/llama-swap
 
-go 1.25.4
+go 1.26.1
 
 require (
 	github.com/billziss-gh/golib v0.2.0

proxy/config/config.go

@@ -124,6 +124,7 @@ type Config struct {
 	LogToStdout        string                 `yaml:"logToStdout"`
 	MetricsMaxInMemory int                    `yaml:"metricsMaxInMemory"`
 	CaptureBuffer      int                    `yaml:"captureBuffer"`
+	GlobalTTL          int                    `yaml:"globalTTL"`
 	Models             map[string]ModelConfig `yaml:"models"` /* key is model ID */
 	Profiles           map[string][]string    `yaml:"profiles"`
 	Groups             map[string]GroupConfig `yaml:"groups"` /* key is group ID */
@@ -203,6 +204,7 @@ func LoadConfigFromReader(r io.Reader) (Config, error) {
 		LogToStdout:        LogToStdoutProxy,
 		MetricsMaxInMemory: 1000,
 		CaptureBuffer:      5,
+		GlobalTTL:          0,
 	}
 	if err = yaml.Unmarshal([]byte(yamlStr), &config); err != nil {
 		return Config{}, err
@@ -216,6 +218,10 @@ func LoadConfigFromReader(r io.Reader) (Config, error) {
 		return Config{}, fmt.Errorf("startPort must be greater than 1")
 	}
 
+	if config.GlobalTTL < 0 {
+		return Config{}, fmt.Errorf("globalTTL must be >= 0")
+	}
+
 	switch config.LogToStdout {
 	case LogToStdoutProxy, LogToStdoutUpstream, LogToStdoutBoth, LogToStdoutNone:
 	default:
@@ -255,6 +261,15 @@ func LoadConfigFromReader(r io.Reader) (Config, error) {
 		modelConfig.Cmd = StripComments(modelConfig.Cmd)
 		modelConfig.CmdStop = StripComments(modelConfig.CmdStop)
 
+		// set model TTL to globalTTL it is the default value
+		if modelConfig.UnloadAfter == MODEL_CONFIG_DEFAULT_TTL {
+			modelConfig.UnloadAfter = config.GlobalTTL
+		}
+
+		if modelConfig.UnloadAfter < 0 {
+			return Config{}, fmt.Errorf("model %s: invalid TTL value %d", modelId, modelConfig.UnloadAfter)
+		}
+
 		// Validate model macros
 		for _, macro := range modelConfig.Macros {
 			if err = validateMacro(macro.Name, macro.Value); err != nil {
@@ -293,6 +308,8 @@ func LoadConfigFromReader(r io.Reader) (Config, error) {
 			modelConfig.Proxy = strings.ReplaceAll(modelConfig.Proxy, macroSlug, macroStr)
 			modelConfig.CheckEndpoint = strings.ReplaceAll(modelConfig.CheckEndpoint, macroSlug, macroStr)
 			modelConfig.Filters.StripParams = strings.ReplaceAll(modelConfig.Filters.StripParams, macroSlug, macroStr)
+			modelConfig.Name = strings.ReplaceAll(modelConfig.Name, macroSlug, macroStr)
+			modelConfig.Description = strings.ReplaceAll(modelConfig.Description, macroSlug, macroStr)
 
 			// Substitute macros in SetParamsByID keys and values
 			if len(modelConfig.Filters.SetParamsByID) > 0 {
@@ -336,6 +353,8 @@ func LoadConfigFromReader(r io.Reader) (Config, error) {
 			modelConfig.Cmd = strings.ReplaceAll(modelConfig.Cmd, macroSlug, macroStr)
 			modelConfig.CmdStop = strings.ReplaceAll(modelConfig.CmdStop, macroSlug, macroStr)
 			modelConfig.Proxy = strings.ReplaceAll(modelConfig.Proxy, macroSlug, macroStr)
+			modelConfig.Name = strings.ReplaceAll(modelConfig.Name, macroSlug, macroStr)
+			modelConfig.Description = strings.ReplaceAll(modelConfig.Description, macroSlug, macroStr)
 
 			if len(modelConfig.Metadata) > 0 {
 				result, err := substituteMacroInValue(modelConfig.Metadata, "PORT", nextPort)
@@ -355,6 +374,8 @@ func LoadConfigFromReader(r io.Reader) (Config, error) {
 			"proxy":               modelConfig.Proxy,
 			"checkEndpoint":       modelConfig.CheckEndpoint,
 			"filters.stripParams": modelConfig.Filters.StripParams,
+			"name":                modelConfig.Name,
+			"description":         modelConfig.Description,
 		}
 
 		for fieldName, fieldValue := range fieldMap {

proxy/config/config_posix_test.go

@@ -187,6 +187,13 @@ groups:
 				Name:             "Model 1",
 				Description:      "This is model 1",
 				SendLoadingState: &modelLoadingState,
+				Timeouts: TimeoutsConfig{
+					Connect:        30,
+					ResponseHeader: 60,
+					TLSHandshake:   10,
+					ExpectContinue: 1,
+					IdleConn:       90,
+				},
 			},
 			"model2": {
 				Cmd:              "path/to/server --arg1 one",
@@ -195,6 +202,13 @@ groups:
 				Env:              []string{},
 				CheckEndpoint:    "/",
 				SendLoadingState: &modelLoadingState,
+				Timeouts: TimeoutsConfig{
+					Connect:        30,
+					ResponseHeader: 60,
+					TLSHandshake:   10,
+					ExpectContinue: 1,
+					IdleConn:       90,
+				},
 			},
 			"model3": {
 				Cmd:              "path/to/cmd --arg1 one",
@@ -203,6 +217,13 @@ groups:
 				Env:              []string{},
 				CheckEndpoint:    "/",
 				SendLoadingState: &modelLoadingState,
+				Timeouts: TimeoutsConfig{
+					Connect:        30,
+					ResponseHeader: 60,
+					TLSHandshake:   10,
+					ExpectContinue: 1,
+					IdleConn:       90,
+				},
 			},
 			"model4": {
 				Cmd:              "path/to/cmd --arg1 one",
@@ -211,6 +232,13 @@ groups:
 				Aliases:          []string{},
 				Env:              []string{},
 				SendLoadingState: &modelLoadingState,
+				Timeouts: TimeoutsConfig{
+					Connect:        30,
+					ResponseHeader: 60,
+					TLSHandshake:   10,
+					ExpectContinue: 1,
+					IdleConn:       90,
+				},
 			},
 		},
 		HealthCheckTimeout: 15,

proxy/config/config_test.go

@@ -6,6 +6,7 @@ import (
 	"testing"
 
 	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
 )
 
 func TestConfig_GroupMemberIsUnique(t *testing.T) {
@@ -848,6 +849,71 @@ func TestConfig_APIKeys_EnvMacros(t *testing.T) {
 	})
 }
 
+func TestConfig_GlobalTTL(t *testing.T) {
+	t.Run("globalTTL sets default for models", func(t *testing.T) {
+		content := `
+globalTTL: 300
+models:
+  model1:
+    cmd: server --port ${PORT}
+`
+		config, err := LoadConfigFromReader(strings.NewReader(content))
+		assert.NoError(t, err)
+		assert.Equal(t, 300, config.GlobalTTL)
+		assert.Equal(t, 300, config.Models["model1"].UnloadAfter)
+	})
+
+	t.Run("model ttl=0 overrides globalTTL", func(t *testing.T) {
+		content := `
+globalTTL: 300
+models:
+  model1:
+    cmd: server --port ${PORT}
+    ttl: 0
+`
+		config, err := LoadConfigFromReader(strings.NewReader(content))
+		assert.NoError(t, err)
+		assert.Equal(t, 0, config.Models["model1"].UnloadAfter)
+	})
+
+	t.Run("model explicit ttl overrides globalTTL", func(t *testing.T) {
+		content := `
+globalTTL: 300
+models:
+  model1:
+    cmd: server --port ${PORT}
+    ttl: 600
+`
+		config, err := LoadConfigFromReader(strings.NewReader(content))
+		assert.NoError(t, err)
+		assert.Equal(t, 600, config.Models["model1"].UnloadAfter)
+	})
+
+	t.Run("globalTTL defaults to 0", func(t *testing.T) {
+		content := `
+models:
+  model1:
+    cmd: server --port ${PORT}
+`
+		config, err := LoadConfigFromReader(strings.NewReader(content))
+		assert.NoError(t, err)
+		assert.Equal(t, 0, config.GlobalTTL)
+		assert.Equal(t, 0, config.Models["model1"].UnloadAfter)
+	})
+
+	t.Run("negative globalTTL rejected", func(t *testing.T) {
+		content := `
+globalTTL: -1
+models:
+  model1:
+    cmd: server --port ${PORT}
+`
+		_, err := LoadConfigFromReader(strings.NewReader(content))
+		assert.Error(t, err)
+		assert.Contains(t, err.Error(), "globalTTL must be >= 0")
+	})
+}
+
 func TestConfig_EnvMacros(t *testing.T) {
 	t.Run("basic env substitution in cmd", func(t *testing.T) {
 		t.Setenv("TEST_MODEL_PATH", "/opt/models")
@@ -1373,3 +1439,108 @@ models:
 	})
 
 }
+
+func TestConfig_TimeoutsParsing(t *testing.T) {
+	configYaml := `
+models:
+  model1:
+    cmd: test-server --port ${PORT}
+    timeouts:
+      connect: 45
+      responseHeader: 120
+`
+
+	config, err := LoadConfigFromReader(strings.NewReader(configYaml))
+	require.NoError(t, err)
+
+	modelConfig, found := config.Models["model1"]
+	require.True(t, found, "model1 should exist in config")
+
+	assert.Equal(t, 45, modelConfig.Timeouts.Connect)
+	assert.Equal(t, 120, modelConfig.Timeouts.ResponseHeader)
+}
+
+func TestConfig_TimeoutsDefaults(t *testing.T) {
+	configYaml := `
+models:
+  model1:
+    cmd: test-server --port ${PORT}
+`
+
+	config, err := LoadConfigFromReader(strings.NewReader(configYaml))
+	require.NoError(t, err)
+
+	modelConfig, found := config.Models["model1"]
+	require.True(t, found, "model1 should exist in config")
+
+	// Default values should be set during unmarshaling
+	assert.Equal(t, 30, modelConfig.Timeouts.Connect)
+	assert.Equal(t, 60, modelConfig.Timeouts.ResponseHeader)
+	assert.Equal(t, 10, modelConfig.Timeouts.TLSHandshake)
+	assert.Equal(t, 1, modelConfig.Timeouts.ExpectContinue)
+	assert.Equal(t, 90, modelConfig.Timeouts.IdleConn)
+}
+
+func TestConfig_TimeoutsZeroAllowed(t *testing.T) {
+	configYaml := `
+models:
+  model1:
+    cmd: test-server --port ${PORT}
+    timeouts:
+      connect: 0
+      responseHeader: 0
+`
+
+	config, err := LoadConfigFromReader(strings.NewReader(configYaml))
+	require.NoError(t, err)
+
+	modelConfig, found := config.Models["model1"]
+	require.True(t, found, "model1 should exist in config")
+
+	// Explicit 0 should be preserved (disables timeout)
+	assert.Equal(t, 0, modelConfig.Timeouts.Connect)
+	assert.Equal(t, 0, modelConfig.Timeouts.ResponseHeader)
+}
+
+func TestConfig_PeerTimeoutsParsing(t *testing.T) {
+	configYaml := `
+peers:
+  peer1:
+    proxy: http://example.com
+    models: [model1]
+    timeouts:
+      connect: 45
+      responseHeader: 120
+`
+
+	config, err := LoadConfigFromReader(strings.NewReader(configYaml))
+	require.NoError(t, err)
+
+	peerConfig, found := config.Peers["peer1"]
+	require.True(t, found, "peer1 should exist in config")
+
+	assert.Equal(t, 45, peerConfig.Timeouts.Connect)
+	assert.Equal(t, 120, peerConfig.Timeouts.ResponseHeader)
+}
+
+func TestConfig_PeerTimeoutsDefaults(t *testing.T) {
+	configYaml := `
+peers:
+  peer1:
+    proxy: http://example.com
+    models: [model1]
+`
+
+	config, err := LoadConfigFromReader(strings.NewReader(configYaml))
+	require.NoError(t, err)
+
+	peerConfig, found := config.Peers["peer1"]
+	require.True(t, found, "peer1 should exist in config")
+
+	// Default values should be set during unmarshaling
+	assert.Equal(t, 30, peerConfig.Timeouts.Connect)
+	assert.Equal(t, 60, peerConfig.Timeouts.ResponseHeader)
+	assert.Equal(t, 10, peerConfig.Timeouts.TLSHandshake)
+	assert.Equal(t, 1, peerConfig.Timeouts.ExpectContinue)
+	assert.Equal(t, 90, peerConfig.Timeouts.IdleConn)
+}

proxy/config/config_windows_test.go

@@ -173,6 +173,13 @@ groups:
 				Env:              []string{"VAR1=value1", "VAR2=value2"},
 				CheckEndpoint:    "/health",
 				SendLoadingState: &modelLoadingState,
+				Timeouts: TimeoutsConfig{
+					Connect:        30,
+					ResponseHeader: 60,
+					TLSHandshake:   10,
+					ExpectContinue: 1,
+					IdleConn:       90,
+				},
 			},
 			"model2": {
 				Cmd:              "path/to/server --arg1 one",
@@ -182,6 +189,13 @@ groups:
 				Env:              []string{},
 				CheckEndpoint:    "/",
 				SendLoadingState: &modelLoadingState,
+				Timeouts: TimeoutsConfig{
+					Connect:        30,
+					ResponseHeader: 60,
+					TLSHandshake:   10,
+					ExpectContinue: 1,
+					IdleConn:       90,
+				},
 			},
 			"model3": {
 				Cmd:              "path/to/cmd --arg1 one",
@@ -191,6 +205,13 @@ groups:
 				Env:              []string{},
 				CheckEndpoint:    "/",
 				SendLoadingState: &modelLoadingState,
+				Timeouts: TimeoutsConfig{
+					Connect:        30,
+					ResponseHeader: 60,
+					TLSHandshake:   10,
+					ExpectContinue: 1,
+					IdleConn:       90,
+				},
 			},
 			"model4": {
 				Cmd:              "path/to/cmd --arg1 one",
@@ -200,6 +221,13 @@ groups:
 				Aliases:          []string{},
 				Env:              []string{},
 				SendLoadingState: &modelLoadingState,
+				Timeouts: TimeoutsConfig{
+					Connect:        30,
+					ResponseHeader: 60,
+					TLSHandshake:   10,
+					ExpectContinue: 1,
+					IdleConn:       90,
+				},
 			},
 		},
 		HealthCheckTimeout: 15,

proxy/config/macro_in_macro_test.go

@@ -104,6 +104,62 @@ models:
 	assert.Contains(t, err.Error(), "self-reference")
 }
 
+// Test macro substitution in name and description fields
+func TestConfig_MacroInNameAndDescription(t *testing.T) {
+	content := `
+startPort: 10000
+macros:
+  "VARIANT": "Q4_K_M"
+  "FAMILY": "llama"
+
+models:
+  my-model:
+    cmd: echo ok
+    proxy: http://localhost:8080
+    name: "${FAMILY} ${VARIANT}"
+    description: "A ${FAMILY} model in ${VARIANT} format"
+`
+
+	config, err := LoadConfigFromReader(strings.NewReader(content))
+	assert.NoError(t, err)
+	assert.Equal(t, "llama Q4_K_M", config.Models["my-model"].Name)
+	assert.Equal(t, "A llama model in Q4_K_M format", config.Models["my-model"].Description)
+}
+
+// Test MODEL_ID macro in name and description fields
+func TestConfig_ModelIDInNameAndDescription(t *testing.T) {
+	content := `
+startPort: 10000
+models:
+  llama-3b:
+    cmd: echo ok
+    proxy: http://localhost:8080
+    name: "Model: ${MODEL_ID}"
+    description: "Running ${MODEL_ID}"
+`
+
+	config, err := LoadConfigFromReader(strings.NewReader(content))
+	assert.NoError(t, err)
+	assert.Equal(t, "Model: llama-3b", config.Models["llama-3b"].Name)
+	assert.Equal(t, "Running llama-3b", config.Models["llama-3b"].Description)
+}
+
+// Test unknown macro in name or description returns an error
+func TestConfig_UnknownMacroInNameDescription(t *testing.T) {
+	content := `
+startPort: 10000
+models:
+  test:
+    cmd: echo ok
+    proxy: http://localhost:8080
+    name: "Model ${UNDEFINED}"
+`
+
+	_, err := LoadConfigFromReader(strings.NewReader(content))
+	assert.Error(t, err)
+	assert.Contains(t, err.Error(), "UNDEFINED")
+}
+
 // Test undefined macro reference error
 func TestConfig_UndefinedMacroReference(t *testing.T) {
 	content := `

proxy/config/model_config.go

@@ -5,6 +5,19 @@ import (
 	"runtime"
 )
 
+const (
+	MODEL_CONFIG_DEFAULT_TTL = -1
+)
+
+// TimeoutsConfig holds timeout settings for proxy connections
+type TimeoutsConfig struct {
+	Connect        int `yaml:"connect"`        // seconds, 0 = no timeout (not recommended)
+	ResponseHeader int `yaml:"responseHeader"` // seconds, 0 = no timeout (not recommended)
+	TLSHandshake   int `yaml:"tlsHandshake"`   // seconds, 0 = no timeout (not recommended)
+	ExpectContinue int `yaml:"expectContinue"` // seconds, 0 = no timeout (not recommended)
+	IdleConn       int `yaml:"idleConn"`       // seconds, 0 = no timeout (not recommended)
+}
+
 type ModelConfig struct {
 	Cmd           string   `yaml:"cmd"`
 	CmdStop       string   `yaml:"cmdStop"`
@@ -36,6 +49,9 @@ type ModelConfig struct {
 
 	// override global setting
 	SendLoadingState *bool `yaml:"sendLoadingState"`
+
+	// Timeout settings for proxy connections
+	Timeouts TimeoutsConfig `yaml:"timeouts"`
 }
 
 func (m *ModelConfig) UnmarshalYAML(unmarshal func(interface{}) error) error {
@@ -47,12 +63,19 @@ func (m *ModelConfig) UnmarshalYAML(unmarshal func(interface{}) error) error {
 		Aliases:          []string{},
 		Env:              []string{},
 		CheckEndpoint:    "/health",
-		UnloadAfter:      0,
+		UnloadAfter:      MODEL_CONFIG_DEFAULT_TTL, // use GlobalTTL
 		Unlisted:         false,
 		UseModelName:     "",
 		ConcurrencyLimit: 0,
 		Name:             "",
 		Description:      "",
+		Timeouts: TimeoutsConfig{
+			Connect:        30,
+			ResponseHeader: 60,
+			TLSHandshake:   10,
+			ExpectContinue: 1,
+			IdleConn:       90,
+		},
 	}
 
 	// the default cmdStop to taskkill /f /t /pid ${PID}

proxy/config/peer.go

@@ -12,6 +12,9 @@ type PeerConfig struct {
 	ApiKey   string   `yaml:"apiKey"`
 	Models   []string `yaml:"models"`
 	Filters  Filters  `yaml:"filters"`
+
+	// Timeout settings for proxy connections
+	Timeouts TimeoutsConfig `yaml:"timeouts"`
 }
 
 func (c *PeerConfig) UnmarshalYAML(unmarshal func(interface{}) error) error {
@@ -21,6 +24,13 @@ func (c *PeerConfig) UnmarshalYAML(unmarshal func(interface{}) error) error {
 		ApiKey:  "",
 		Models:  []string{},
 		Filters: Filters{},
+		Timeouts: TimeoutsConfig{
+			Connect:        30,
+			ResponseHeader: 60,
+			TLSHandshake:   10,
+			ExpectContinue: 1,
+			IdleConn:       90,
+		},
 	}
 
 	if err := unmarshal(&defaults); err != nil {

proxy/metrics_monitor.go

@@ -350,6 +350,11 @@ func processStreamingResponse(modelID string, start time.Time, body []byte) (Tok
 			usage := parsed.Get("usage")
 			timings := parsed.Get("timings")
 
+			// v1/responses format nests usage under response.usage
+			if !usage.Exists() {
+				usage = parsed.Get("response.usage")
+			}
+
 			if usage.Exists() || timings.Exists() {
 				return parseMetrics(modelID, start, usage, timings)
 			}
@@ -360,6 +365,8 @@ func processStreamingResponse(modelID string, start time.Time, body []byte) (Tok
 }
 
 func parseMetrics(modelID string, start time.Time, usage, timings gjson.Result) (TokenMetrics, error) {
+	wallDurationMs := int(time.Since(start).Milliseconds())
+
 	// default values
 	cachedTokens := -1 // unknown or missing data
 	outputTokens := 0
@@ -368,7 +375,7 @@ func parseMetrics(modelID string, start time.Time, usage, timings gjson.Result)
 	// timings data
 	tokensPerSecond := -1.0
 	promptPerSecond := -1.0
-	durationMs := int(time.Since(start).Milliseconds())
+	durationMs := wallDurationMs
 
 	if usage.Exists() {
 		if pt := usage.Get("prompt_tokens"); pt.Exists() {
@@ -397,7 +404,10 @@ func parseMetrics(modelID string, start time.Time, usage, timings gjson.Result)
 		outputTokens = int(timings.Get("predicted_n").Int())
 		promptPerSecond = timings.Get("prompt_per_second").Float()
 		tokensPerSecond = timings.Get("predicted_per_second").Float()
-		durationMs = int(timings.Get("prompt_ms").Float() + timings.Get("predicted_ms").Float())
+		timingsDurationMs := int(timings.Get("prompt_ms").Float() + timings.Get("predicted_ms").Float())
+		if timingsDurationMs > durationMs {
+			durationMs = timingsDurationMs
+		}
 
 		if cachedValue := timings.Get("cache_n"); cachedValue.Exists() {
 			cachedTokens = int(cachedValue.Int())
@@ -503,9 +513,9 @@ func filterAcceptEncoding(acceptEncoding string) string {
 	supported := map[string]bool{"gzip": true, "deflate": true}
 	var filtered []string
 
-	for _, part := range strings.Split(acceptEncoding, ",") {
+	for part := range strings.SplitSeq(acceptEncoding, ",") {
 		// Parse encoding and optional quality value (e.g., "gzip;q=1.0")
-		encoding := strings.TrimSpace(strings.Split(part, ";")[0])
+		encoding, _, _ := strings.Cut(strings.TrimSpace(part), ";")
 		if supported[strings.ToLower(encoding)] {
 			filtered = append(filtered, strings.TrimSpace(part))
 		}

proxy/metrics_monitor_test.go

@@ -14,6 +14,7 @@ import (
 	"github.com/gin-gonic/gin"
 	"github.com/mostlygeek/llama-swap/event"
 	"github.com/stretchr/testify/assert"
+	"github.com/tidwall/gjson"
 )
 
 func TestMetricsMonitor_AddMetrics(t *testing.T) {
@@ -570,6 +571,27 @@ func TestMetricsMonitor_Concurrent(t *testing.T) {
 }
 
 func TestMetricsMonitor_ParseMetrics(t *testing.T) {
+	t.Run("keeps wall clock duration when timings underreport request time", func(t *testing.T) {
+		start := time.Now().Add(-5 * time.Second)
+		usage := gjson.Parse(`{"prompt_tokens": 5, "completion_tokens": 1}`)
+		timings := gjson.Parse(`{
+			"prompt_n": 5,
+			"predicted_n": 1,
+			"prompt_per_second": 10.0,
+			"predicted_per_second": 2.0,
+			"prompt_ms": 5.0,
+			"predicted_ms": 15.0
+		}`)
+
+		metrics, err := parseMetrics("test-model", start, usage, timings)
+		assert.NoError(t, err)
+		assert.Equal(t, 5, metrics.InputTokens)
+		assert.Equal(t, 1, metrics.OutputTokens)
+		assert.Equal(t, 10.0, metrics.PromptPerSecond)
+		assert.Equal(t, 2.0, metrics.TokensPerSecond)
+		assert.GreaterOrEqual(t, metrics.DurationMs, 5000)
+	})
+
 	t.Run("prefers timings over usage data", func(t *testing.T) {
 		mm := newMetricsMonitor(testLogger, 10, 0)
 
@@ -709,6 +731,35 @@ data: [DONE]
 		assert.Equal(t, 0, metrics[0].OutputTokens)
 	})
 
+	t.Run("v1/responses format with nested response.usage", func(t *testing.T) {
+		mm := newMetricsMonitor(testLogger, 10, 0)
+
+		// v1/responses SSE format: usage is nested under response.usage
+		responseBody := "event: response.completed\n" +
+			`data: {"type":"response.completed","response":{"id":"resp_abc","object":"response","created_at":1773416985,"status":"completed","model":"test-model","output":[],"usage":{"input_tokens":17,"output_tokens":23,"total_tokens":40}}}` +
+			"\n\n"
+
+		nextHandler := func(modelID string, w http.ResponseWriter, r *http.Request) error {
+			w.Header().Set("Content-Type", "text/event-stream")
+			w.WriteHeader(http.StatusOK)
+			w.Write([]byte(responseBody))
+			return nil
+		}
+
+		req := httptest.NewRequest("POST", "/v1/responses", nil)
+		rec := httptest.NewRecorder()
+		ginCtx, _ := gin.CreateTestContext(rec)
+
+		err := mm.wrapHandler("test-model", ginCtx.Writer, req, nextHandler)
+		assert.NoError(t, err)
+
+		metrics := mm.getMetrics()
+		assert.Equal(t, 1, len(metrics))
+		assert.Equal(t, "test-model", metrics[0].Model)
+		assert.Equal(t, 17, metrics[0].InputTokens)
+		assert.Equal(t, 23, metrics[0].OutputTokens)
+	})
+
 	t.Run("handles empty streaming response records minimal metrics", func(t *testing.T) {
 		mm := newMetricsMonitor(testLogger, 10, 0)
 

proxy/peerproxy.go

@@ -34,23 +34,25 @@ func NewPeerProxy(peers config.PeerDictionaryConfig, proxyLogger *LogMonitor) (*
 	}
 	sort.Strings(peerIDs)
 
-	// Create a shared transport with reasonable timeouts for peer connections
-	// these can be tuned with feedback later
-	peerTransport := &http.Transport{
-		DialContext: (&net.Dialer{
-			Timeout:   30 * time.Second, // Connection timeout
-			KeepAlive: 30 * time.Second,
-		}).DialContext,
-		TLSHandshakeTimeout:   10 * time.Second,
-		ResponseHeaderTimeout: 60 * time.Second, // Time to wait for response headers
-		ExpectContinueTimeout: 1 * time.Second,
-		MaxIdleConns:          100,
-		MaxIdleConnsPerHost:   10,
-		IdleConnTimeout:       90 * time.Second,
-	}
-
 	for _, peerID := range peerIDs {
 		peer := peers[peerID]
+
+		// Create a transport with per-peer timeout configuration
+		peerTransport := &http.Transport{
+			Proxy: http.ProxyFromEnvironment,
+			DialContext: (&net.Dialer{
+				Timeout:   time.Duration(peer.Timeouts.Connect) * time.Second,
+				KeepAlive: 30 * time.Second,
+			}).DialContext,
+			TLSHandshakeTimeout:   time.Duration(peer.Timeouts.TLSHandshake) * time.Second,
+			ResponseHeaderTimeout: time.Duration(peer.Timeouts.ResponseHeader) * time.Second,
+			ExpectContinueTimeout: time.Duration(peer.Timeouts.ExpectContinue) * time.Second,
+			ForceAttemptHTTP2:     true,
+			MaxIdleConns:          100,
+			MaxIdleConnsPerHost:   10,
+			IdleConnTimeout:       time.Duration(peer.Timeouts.IdleConn) * time.Second,
+		}
+
 		// Create reverse proxy for this peer
 		reverseProxy := httputil.NewSingleHostReverseProxy(peer.ProxyURL)
 		reverseProxy.Transport = peerTransport

proxy/peerproxy_test.go

@@ -6,6 +6,7 @@ import (
 	"net/url"
 	"strings"
 	"testing"
+	"time"
 
 	"github.com/mostlygeek/llama-swap/proxy/config"
 	"github.com/stretchr/testify/assert"
@@ -266,3 +267,45 @@ func TestProxyRequest_SSEHeaderModification(t *testing.T) {
 	// The X-Accel-Buffering header should be set to "no" for SSE
 	assert.Equal(t, "no", w.Header().Get("X-Accel-Buffering"))
 }
+
+func TestNewPeerProxy_CustomTimeouts(t *testing.T) {
+	proxyURL, _ := url.Parse("http://localhost:8080")
+
+	peers := config.PeerDictionaryConfig{
+		"test-peer": config.PeerConfig{
+			Proxy:    "http://localhost:8080",
+			ProxyURL: proxyURL,
+			Models:   []string{"model1"},
+			Timeouts: config.TimeoutsConfig{
+				Connect:        45,
+				ResponseHeader: 300,
+				TLSHandshake:   15,
+				ExpectContinue: 2,
+				IdleConn:       120,
+			},
+		},
+	}
+
+	peerProxy, err := NewPeerProxy(peers, testLogger)
+
+	assert.NoError(t, err)
+	assert.NotNil(t, peerProxy)
+	assert.True(t, peerProxy.HasPeerModel("model1"))
+
+	// Verify the timeout values are actually applied to the transport
+	member, found := peerProxy.proxyMap["model1"]
+	require.True(t, found, "model1 should exist in proxyMap")
+	assert.NotNil(t, member.reverseProxy)
+	assert.NotNil(t, member.reverseProxy.Transport)
+
+	transport, ok := member.reverseProxy.Transport.(*http.Transport)
+	require.True(t, ok, "Transport should be *http.Transport")
+
+	// Verify all timeout values are correctly applied
+	assert.Equal(t, 300*time.Second, transport.ResponseHeaderTimeout)
+	assert.Equal(t, 15*time.Second, transport.TLSHandshakeTimeout)
+	assert.Equal(t, 2*time.Second, transport.ExpectContinueTimeout)
+	assert.Equal(t, 120*time.Second, transport.IdleConnTimeout)
+	// ForceAttemptHTTP2 should be enabled
+	assert.True(t, transport.ForceAttemptHTTP2)
+}

proxy/process.go

@@ -96,6 +96,24 @@ func NewProcess(ID string, healthCheckTimeout int, config config.ModelConfig, pr
 	var reverseProxy *httputil.ReverseProxy
 	if proxyURL != nil {
 		reverseProxy = httputil.NewSingleHostReverseProxy(proxyURL)
+
+		// Create custom transport with configured timeouts
+		transport := &http.Transport{
+			Proxy: http.ProxyFromEnvironment,
+			DialContext: (&net.Dialer{
+				Timeout:   time.Duration(config.Timeouts.Connect) * time.Second,
+				KeepAlive: 30 * time.Second,
+			}).DialContext,
+			TLSHandshakeTimeout:   time.Duration(config.Timeouts.TLSHandshake) * time.Second,
+			ResponseHeaderTimeout: time.Duration(config.Timeouts.ResponseHeader) * time.Second,
+			ExpectContinueTimeout: time.Duration(config.Timeouts.ExpectContinue) * time.Second,
+			ForceAttemptHTTP2:     true,
+			MaxIdleConns:          100,
+			MaxIdleConnsPerHost:   10,
+			IdleConnTimeout:       time.Duration(config.Timeouts.IdleConn) * time.Second,
+		}
+		reverseProxy.Transport = transport
+
 		reverseProxy.ModifyResponse = func(resp *http.Response) error {
 			// prevent nginx from buffering streaming responses (e.g., SSE)
 			if strings.Contains(strings.ToLower(resp.Header.Get("Content-Type")), "text/event-stream") {

proxy/process_test.go

@@ -2,6 +2,7 @@ package proxy
 
 import (
 	"fmt"
+	"io"
 	"net/http"
 	"net/http/httptest"
 	"os"
@@ -117,12 +118,12 @@ func TestProcess_UnloadAfterTTL(t *testing.T) {
 	}
 
 	expectedMessage := "I_sense_imminent_danger"
-	config := getTestSimpleResponderConfig(expectedMessage)
-	assert.Equal(t, 0, config.UnloadAfter)
-	config.UnloadAfter = 3 // seconds
-	assert.Equal(t, 3, config.UnloadAfter)
+	conf := getTestSimpleResponderConfig(expectedMessage)
+	assert.Equal(t, config.MODEL_CONFIG_DEFAULT_TTL, conf.UnloadAfter)
+	conf.UnloadAfter = 3 // seconds
+	assert.Equal(t, 3, conf.UnloadAfter)
 
-	process := NewProcess("ttl_test", 2, config, debugLogger, debugLogger)
+	process := NewProcess("ttl_test", 2, conf, debugLogger, debugLogger)
 	defer process.Stop()
 
 	// this should take 4 seconds
@@ -159,12 +160,12 @@ func TestProcess_LowTTLValue(t *testing.T) {
 		t.Skip("skipping test, edit process_test.go to run it ")
 	}
 
-	config := getTestSimpleResponderConfig("fast_ttl")
-	assert.Equal(t, 0, config.UnloadAfter)
-	config.UnloadAfter = 1 // second
-	assert.Equal(t, 1, config.UnloadAfter)
+	conf := getTestSimpleResponderConfig("fast_ttl")
+	assert.Equal(t, config.MODEL_CONFIG_DEFAULT_TTL, conf.UnloadAfter)
+	conf.UnloadAfter = 1 // second
+	assert.Equal(t, 1, conf.UnloadAfter)
 
-	process := NewProcess("ttl", 2, config, debugLogger, debugLogger)
+	process := NewProcess("ttl", 2, conf, debugLogger, debugLogger)
 	defer process.Stop()
 
 	for i := 0; i < 100; i++ {
@@ -569,3 +570,39 @@ func (w *panicOnWriteResponseWriter) Write(b []byte) (int, error) {
 	}
 	return w.ResponseRecorder.Write(b)
 }
+
+func TestProcess_CustomTimeouts(t *testing.T) {
+	modelConfig := config.ModelConfig{
+		Cmd:           "echo test",
+		Proxy:         "http://localhost:8080",
+		CheckEndpoint: "/health",
+		Timeouts: config.TimeoutsConfig{
+			Connect:        45,
+			ResponseHeader: 120,
+			TLSHandshake:   15,
+			ExpectContinue: 2,
+			IdleConn:       120,
+		},
+	}
+
+	debugLogger := NewLogMonitorWriter(io.Discard)
+	process := NewProcess("test-model", 30, modelConfig, debugLogger, debugLogger)
+
+	// Verify the process was created successfully
+	assert.NotNil(t, process)
+	assert.Equal(t, "test-model", process.ID)
+	assert.NotNil(t, process.reverseProxy)
+	assert.NotNil(t, process.reverseProxy.Transport)
+
+	// Verify it's using http.Transport (not some other type)
+	transport, ok := process.reverseProxy.Transport.(*http.Transport)
+	assert.True(t, ok, "Transport should be *http.Transport")
+	assert.NotNil(t, transport)
+
+	// Verify the timeouts are correctly applied
+	assert.Equal(t, 120*time.Second, transport.ResponseHeaderTimeout)
+	assert.Equal(t, 15*time.Second, transport.TLSHandshakeTimeout)
+	assert.Equal(t, 2*time.Second, transport.ExpectContinueTimeout)
+	assert.Equal(t, 120*time.Second, transport.IdleConnTimeout)
+	assert.True(t, transport.ForceAttemptHTTP2)
+}

proxy/proxymanager.go

@@ -346,6 +346,11 @@ func (pm *ProxyManager) setupGinEngine() {
 	pm.ginEngine.POST("/v1/images/generations", pm.apiKeyAuth(), pm.trackInflight(), pm.proxyInferenceHandler)
 	pm.ginEngine.POST("/v1/images/edits", pm.apiKeyAuth(), pm.trackInflight(), pm.proxyOAIPostFormHandler)
 
+	// sd.cpp /sdapi/v1 endpoints
+	pm.ginEngine.POST("/sdapi/v1/txt2img", pm.apiKeyAuth(), pm.trackInflight(), pm.proxyInferenceHandler)
+	pm.ginEngine.POST("/sdapi/v1/img2img", pm.apiKeyAuth(), pm.trackInflight(), pm.proxyInferenceHandler)
+	pm.ginEngine.GET("/sdapi/v1/loras", pm.apiKeyAuth(), pm.trackInflight(), pm.proxyGETModelHandler)
+
 	pm.ginEngine.GET("/v1/models", pm.apiKeyAuth(), pm.listModelsHandler)
 
 	// in proxymanager_loghandlers.go

proxy/proxymanager_test.go

@@ -730,7 +730,7 @@ func TestProxyManager_RunningEndpoint(t *testing.T) {
 		// Verify extended fields are present
 		assert.NotEmpty(t, response.Running[0].Cmd, "cmd should be populated")
 		assert.NotEmpty(t, response.Running[0].Proxy, "proxy should be populated")
-		assert.Equal(t, 0, response.Running[0].TTL, "ttl should default to 0")
+		assert.Equal(t, -1, response.Running[0].TTL, "ttl should default to -1 (use globalTTL)")
 	})
 }
 
@@ -1659,3 +1659,82 @@ models:
 		assert.Equal(t, "no", w.Header().Get("X-Accel-Buffering"))
 	})
 }
+
+func TestProxyManager_SdApiTxt2ImgRouting(t *testing.T) {
+	conf := config.AddDefaultGroupToConfig(config.Config{
+		HealthCheckTimeout: 15,
+		Models: map[string]config.ModelConfig{
+			"sd-model": getTestSimpleResponderConfig("sd-model"),
+		},
+		LogLevel: "error",
+	})
+
+	proxy := New(conf)
+	defer proxy.StopProcesses(StopWaitForInflightRequest)
+
+	t.Run("successful txt2img with model", func(t *testing.T) {
+		reqBody := `{"model":"sd-model","prompt":"a cat"}`
+		req := httptest.NewRequest("POST", "/sdapi/v1/txt2img", bytes.NewBufferString(reqBody))
+		w := CreateTestResponseRecorder()
+
+		proxy.ServeHTTP(w, req)
+		assert.Equal(t, http.StatusOK, w.Code)
+		assert.Contains(t, w.Body.String(), "sd-model")
+	})
+
+	t.Run("successful img2img with model", func(t *testing.T) {
+		reqBody := `{"model":"sd-model","prompt":"a cat","init_images":[]}`
+		req := httptest.NewRequest("POST", "/sdapi/v1/img2img", bytes.NewBufferString(reqBody))
+		w := CreateTestResponseRecorder()
+
+		proxy.ServeHTTP(w, req)
+		assert.Equal(t, http.StatusOK, w.Code)
+		assert.Contains(t, w.Body.String(), "sd-model")
+	})
+
+	t.Run("missing model returns 400", func(t *testing.T) {
+		reqBody := `{"prompt":"a cat"}`
+		req := httptest.NewRequest("POST", "/sdapi/v1/txt2img", bytes.NewBufferString(reqBody))
+		w := CreateTestResponseRecorder()
+
+		proxy.ServeHTTP(w, req)
+		assert.Equal(t, http.StatusBadRequest, w.Code)
+		assert.Contains(t, w.Body.String(), "missing or invalid 'model' key")
+	})
+}
+
+func TestProxyManager_SdApiGetLoras(t *testing.T) {
+	conf := config.AddDefaultGroupToConfig(config.Config{
+		HealthCheckTimeout: 15,
+		Models: map[string]config.ModelConfig{
+			"sd-model": getTestSimpleResponderConfig("sd-model"),
+		},
+		LogLevel: "error",
+	})
+
+	proxy := New(conf)
+	defer proxy.StopProcesses(StopWaitForInflightRequest)
+
+	t.Run("successful GET loras with model query param", func(t *testing.T) {
+		req := httptest.NewRequest("GET", "/sdapi/v1/loras?model=sd-model", nil)
+		w := CreateTestResponseRecorder()
+		proxy.ServeHTTP(w, req)
+		assert.Equal(t, http.StatusOK, w.Code)
+	})
+
+	t.Run("missing model query param returns 400", func(t *testing.T) {
+		req := httptest.NewRequest("GET", "/sdapi/v1/loras", nil)
+		w := CreateTestResponseRecorder()
+		proxy.ServeHTTP(w, req)
+		assert.Equal(t, http.StatusBadRequest, w.Code)
+		assert.Contains(t, w.Body.String(), "missing required 'model' query parameter")
+	})
+
+	t.Run("unknown model returns 400", func(t *testing.T) {
+		req := httptest.NewRequest("GET", "/sdapi/v1/loras?model=nonexistent", nil)
+		w := CreateTestResponseRecorder()
+		proxy.ServeHTTP(w, req)
+		assert.Equal(t, http.StatusBadRequest, w.Code)
+		assert.Contains(t, w.Body.String(), "could not find suitable handler")
+	})
+}

ui-svelte/.npmrc

@@ -0,0 +1 @@
+legacy-peer-deps=true

ui-svelte/package.json

@@ -12,18 +12,18 @@
     "test:watch": "vitest"
   },
   "devDependencies": {
-    "@sveltejs/vite-plugin-svelte": "^5.0.3",
+    "@sveltejs/vite-plugin-svelte": "^7.0.0",
     "@tailwindcss/vite": "^4.1.8",
     "@tsconfig/svelte": "^5.0.4",
     "@types/hast": "^3.0.4",
     "@types/node": "^25.1.0",
-    "svelte": "^5.19.0",
+    "svelte": "^5.46.4",
     "svelte-check": "^4.1.4",
     "tailwindcss": "^4.1.8",
     "typescript": "~5.8.3",
-    "vite": "^6.3.5",
-    "vite-plugin-compression2": "^2.4.0",
-    "vitest": "^4.0.18"
+    "vite": "^8.0.0",
+    "vite-plugin-compression2": "^2.5.1",
+    "vitest": "^4.1.0"
   },
   "dependencies": {
     "highlight.js": "^11.11.1",

ui-svelte/src/components/playground/ChatMessage.svelte

@@ -116,6 +116,47 @@
       cancelEdit();
     }
   }
+
+  const COPY_SVG = `<svg xmlns="http://www.w3.org/2000/svg" width="14" height="14" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round"><rect width="14" height="14" x="8" y="8" rx="2" ry="2"/><path d="M4 16c-1.1 0-2-.9-2-2V4c0-1.1.9-2 2-2h10c1.1 0 2 .9 2 2"/></svg>`;
+  const CHECK_SVG = `<svg xmlns="http://www.w3.org/2000/svg" width="14" height="14" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round"><path d="M20 6 9 17l-5-5"/></svg>`;
+
+  function codeBlockCopy(node: HTMLElement) {
+    function attachButtons() {
+      node.querySelectorAll<HTMLPreElement>('pre:not([data-copy-btn])').forEach(pre => {
+        pre.setAttribute('data-copy-btn', 'true');
+        const btn = document.createElement('button');
+        btn.className = 'code-copy-btn';
+        btn.title = 'Copy code';
+        btn.innerHTML = COPY_SVG;
+        btn.addEventListener('click', async () => {
+          const text = pre.querySelector('code')?.textContent ?? pre.textContent ?? '';
+          try {
+            if (navigator.clipboard && window.isSecureContext) {
+              await navigator.clipboard.writeText(text);
+            } else {
+              const ta = document.createElement('textarea');
+              ta.value = text;
+              ta.style.cssText = 'position:fixed;left:-9999px';
+              document.body.appendChild(ta);
+              ta.select();
+              document.execCommand('copy');
+              document.body.removeChild(ta);
+            }
+            btn.innerHTML = CHECK_SVG;
+            btn.classList.add('copied');
+            setTimeout(() => { btn.innerHTML = COPY_SVG; btn.classList.remove('copied'); }, 2000);
+          } catch (e) {
+            console.error('copy failed', e);
+          }
+        });
+        pre.appendChild(btn);
+      });
+    }
+    attachButtons();
+    const mo = new MutationObserver(attachButtons);
+    mo.observe(node, { childList: true, subtree: true });
+    return { destroy: () => mo.disconnect() };
+  }
 </script>
 
 <div class="flex {role === 'user' ? 'justify-end' : 'justify-start'} mb-4">
@@ -174,7 +215,7 @@
       {#if showRaw}
         <div class="whitespace-pre-wrap font-mono text-sm">{textContent}</div>
       {:else}
-        <div class="prose prose-sm dark:prose-invert max-w-none">
+        <div class="prose prose-sm dark:prose-invert max-w-none" use:codeBlockCopy>
           {#each renderedParts.blocks as block (block.id)}
             {@html block.html}
           {/each}
@@ -299,14 +340,42 @@
 
 <style>
   .prose :global(pre) {
+    position: relative;
     background-color: var(--color-surface);
     border: 1px solid var(--color-border, rgba(128, 128, 128, 0.2));
     border-radius: 0.375rem;
     padding: 0.75rem;
+    padding-right: 2.5rem;
     overflow-x: auto;
     margin: 0.5rem 0;
   }
 
+  .prose :global(.code-copy-btn) {
+    position: absolute;
+    top: 0.375rem;
+    right: 0.375rem;
+    display: flex;
+    align-items: center;
+    justify-content: center;
+    padding: 0.25rem;
+    border-radius: 0.25rem;
+    border: 1px solid var(--color-border);
+    background: var(--color-surface);
+    color: var(--color-txtsecondary);
+    cursor: pointer;
+    transition: background-color 0.15s;
+    line-height: 0;
+  }
+
+  .prose :global(.code-copy-btn:hover) {
+    background: var(--color-secondary);
+  }
+
+  .prose :global(.code-copy-btn.copied) {
+    color: var(--color-success);
+    opacity: 1;
+  }
+
   .prose :global(code) {
     font-family: ui-monospace, SFMono-Regular, Menlo, Monaco, Consolas, monospace;
     font-size: 0.875em;

ui-svelte/src/components/playground/ImageInterface.svelte

@@ -2,26 +2,91 @@
   import { models } from "../../stores/api";
   import { persistentStore } from "../../stores/persistent";
   import { generateImage } from "../../lib/imageApi";
+  import { generateSdImage, fetchSdLoras } from "../../lib/sdApi";
   import { playgroundStores } from "../../stores/playgroundActivity";
   import ModelSelector from "./ModelSelector.svelte";
   import ExpandableTextarea from "./ExpandableTextarea.svelte";
+  import type { ImageApiMode, SdApiLora, SdApiLoraRef } from "../../lib/types";
 
   const selectedModelStore = persistentStore<string>("playground-image-model", "");
   const selectedSizeStore = persistentStore<string>("playground-image-size", "1024x1024");
+  const apiModeStore = persistentStore<ImageApiMode>("playground-image-api-mode", "openai");
+
+  // SDAPI persistent settings
+  const sdNegativePromptStore = persistentStore<string>("playground-sdapi-negative-prompt", "");
+  const sdStepsStore = persistentStore<number>("playground-sdapi-steps", 20);
+  const sdCfgScaleStore = persistentStore<number>("playground-sdapi-cfg-scale", 7);
+  const sdSeedStore = persistentStore<number>("playground-sdapi-seed", -1);
+  const sdSamplerStore = persistentStore<string>("playground-sdapi-sampler", "");
+  const sdSchedulerStore = persistentStore<string>("playground-sdapi-scheduler", "");
+  const sdBatchSizeStore = persistentStore<number>("playground-sdapi-batch-size", 1);
 
   let prompt = $state("");
   let isGenerating = $state(false);
-  let generatedImage = $state<string | null>(null);
+  let generatedImages = $state<string[]>([]);
   let error = $state<string | null>(null);
   let abortController = $state<AbortController | null>(null);
   let showFullscreen = $state(false);
+  let fullscreenIndex = $state(0);
+  let showSettings = $state(false);
+
+  // SDAPI lora state
+  let availableLoras = $state<SdApiLora[]>([]);
+  let selectedLoras = $state<SdApiLoraRef[]>([]);
+  let isLoadingLoras = $state(false);
+  let lorasLoaded = $state(false);
+  let loraError = $state<string | null>(null);
 
   let hasModels = $derived($models.some((m) => !m.unlisted));
+  let isSdapi = $derived($apiModeStore === "sdapi");
 
   $effect(() => {
     playgroundStores.imageGenerating.set(isGenerating);
   });
 
+  async function loadLoras() {
+    if (!$selectedModelStore || isLoadingLoras) return;
+    isLoadingLoras = true;
+    loraError = null;
+    try {
+      const loras = await fetchSdLoras($selectedModelStore);
+      availableLoras = loras;
+      lorasLoaded = true;
+    } catch (err) {
+      availableLoras = [];
+      loraError = err instanceof Error ? err.message : "Failed to load LoRAs";
+      lorasLoaded = false;
+    } finally {
+      isLoadingLoras = false;
+    }
+  }
+
+  function addLora(event: Event) {
+    const select = event.target as HTMLSelectElement;
+    const path = select.value;
+    if (!path) return;
+
+    const lora = availableLoras.find((l) => l.path === path);
+    if (lora && !selectedLoras.some((l) => l.path === path)) {
+      selectedLoras = [...selectedLoras, { path: lora.path, multiplier: 1.0 }];
+    }
+    select.value = "";
+  }
+
+  function removeLora(path: string) {
+    selectedLoras = selectedLoras.filter((l) => l.path !== path);
+  }
+
+  function updateLoraMultiplier(path: string, multiplier: number) {
+    selectedLoras = selectedLoras.map((l) =>
+      l.path === path ? { ...l, multiplier } : l
+    );
+  }
+
+  function getLoraName(path: string): string {
+    return availableLoras.find((l) => l.path === path)?.name ?? path;
+  }
+
   async function generate() {
     const trimmedPrompt = prompt.trim();
     if (!trimmedPrompt || !$selectedModelStore || isGenerating) return;
@@ -31,19 +96,44 @@
     abortController = new AbortController();
 
     try {
-      const response = await generateImage(
-        $selectedModelStore,
-        trimmedPrompt,
-        $selectedSizeStore,
-        abortController.signal
-      );
+      if (isSdapi) {
+        const [w, h] = $selectedSizeStore.split("x").map(Number);
+        const request = {
+          model: $selectedModelStore,
+          prompt: trimmedPrompt,
+          negative_prompt: $sdNegativePromptStore || undefined,
+          width: w,
+          height: h,
+          steps: $sdStepsStore,
+          cfg_scale: $sdCfgScaleStore,
+          seed: $sdSeedStore,
+          batch_size: $sdBatchSizeStore,
+          sampler_name: $sdSamplerStore || undefined,
+          scheduler: $sdSchedulerStore || undefined,
+          lora: selectedLoras.length > 0 ? selectedLoras : undefined,
+        };
 
-      if (response.data && response.data.length > 0) {
-        const imageData = response.data[0];
-        if (imageData.b64_json) {
-          generatedImage = `data:image/png;base64,${imageData.b64_json}`;
-        } else if (imageData.url) {
-          generatedImage = imageData.url;
+        const response = await generateSdImage(request, abortController.signal);
+        if (response.images && response.images.length > 0) {
+          generatedImages = response.images.map(
+            (img) => `data:image/png;base64,${img}`
+          );
+        }
+      } else {
+        const response = await generateImage(
+          $selectedModelStore,
+          trimmedPrompt,
+          $selectedSizeStore,
+          abortController.signal
+        );
+
+        if (response.data && response.data.length > 0) {
+          const imageData = response.data[0];
+          if (imageData.b64_json) {
+            generatedImages = [`data:image/png;base64,${imageData.b64_json}`];
+          } else if (imageData.url) {
+            generatedImages = [imageData.url];
+          }
         }
       }
     } catch (err) {
@@ -63,28 +153,29 @@
   }
 
   function clearImage() {
-    generatedImage = null;
+    generatedImages = [];
     error = null;
     prompt = "";
   }
 
-  function downloadImage() {
-    if (!generatedImage) return;
+  function downloadImage(index: number = 0) {
+    const img = generatedImages[index];
+    if (!img) return;
 
     const link = document.createElement("a");
-    link.href = generatedImage;
-    link.download = `generated-image-${Date.now()}.png`;
+    link.href = img;
+    link.download = `generated-image-${Date.now()}-${index}.png`;
     document.body.appendChild(link);
     link.click();
     document.body.removeChild(link);
   }
 
-  function openFullscreen() {
+  function openFullscreen(index: number = 0) {
+    fullscreenIndex = index;
     showFullscreen = true;
   }
 
   function closeFullscreen(event?: MouseEvent) {
-    // Only close if clicking the background, not the image
     if (event && event.target !== event.currentTarget) {
       return;
     }
@@ -100,9 +191,19 @@
 </script>
 
 <div class="flex flex-col h-full">
-  <!-- Model selector -->
+  <!-- Model selector and mode toggle -->
   <div class="shrink-0 flex flex-wrap gap-2 mb-4">
     <ModelSelector bind:value={$selectedModelStore} placeholder="Select an image model..." disabled={isGenerating} />
+
+    <select
+      class="px-3 py-2 rounded border border-gray-200 dark:border-white/10 bg-surface focus:outline-none focus:ring-2 focus:ring-primary"
+      bind:value={$apiModeStore}
+      disabled={isGenerating}
+    >
+      <option value="openai">OpenAI</option>
+      <option value="sdapi">SDAPI</option>
+    </select>
+
     <select
       class="px-3 py-2 rounded border border-gray-200 dark:border-white/10 bg-surface focus:outline-none focus:ring-2 focus:ring-primary"
       bind:value={$selectedSizeStore}
@@ -123,8 +224,166 @@
         <option value="1024x1792">1024x1792 (SDXL)</option>
       </optgroup>
     </select>
+
+    {#if isSdapi}
+      <button
+        class="px-3 py-2 rounded border border-gray-200 dark:border-white/10 bg-surface hover:bg-secondary-hover transition-colors"
+        onclick={() => showSettings = !showSettings}
+      >
+        {showSettings ? "Hide Settings" : "Settings"}
+      </button>
+    {/if}
   </div>
 
+  <!-- SDAPI Settings Panel -->
+  {#if isSdapi && showSettings}
+    <div class="shrink-0 mb-4 p-4 rounded border border-gray-200 dark:border-white/10 bg-surface">
+      <div class="grid grid-cols-2 md:grid-cols-4 gap-3 mb-3">
+        <label class="flex flex-col gap-1">
+          <span class="text-xs text-txtsecondary">Steps</span>
+          <input
+            type="number"
+            class="px-2 py-1 rounded border border-gray-200 dark:border-white/10 bg-surface focus:outline-none focus:ring-2 focus:ring-primary"
+            bind:value={$sdStepsStore}
+            min="1"
+            max="150"
+          />
+        </label>
+        <label class="flex flex-col gap-1">
+          <span class="text-xs text-txtsecondary">CFG Scale</span>
+          <input
+            type="number"
+            class="px-2 py-1 rounded border border-gray-200 dark:border-white/10 bg-surface focus:outline-none focus:ring-2 focus:ring-primary"
+            bind:value={$sdCfgScaleStore}
+            min="1"
+            max="30"
+            step="0.5"
+          />
+        </label>
+        <label class="flex flex-col gap-1">
+          <span class="text-xs text-txtsecondary">Seed (-1 = random)</span>
+          <input
+            type="number"
+            class="px-2 py-1 rounded border border-gray-200 dark:border-white/10 bg-surface focus:outline-none focus:ring-2 focus:ring-primary"
+            bind:value={$sdSeedStore}
+            min="-1"
+          />
+        </label>
+        <label class="flex flex-col gap-1">
+          <span class="text-xs text-txtsecondary">Batch Size</span>
+          <input
+            type="number"
+            class="px-2 py-1 rounded border border-gray-200 dark:border-white/10 bg-surface focus:outline-none focus:ring-2 focus:ring-primary"
+            bind:value={$sdBatchSizeStore}
+            min="1"
+            max="8"
+          />
+        </label>
+        <label class="flex flex-col gap-1">
+          <span class="text-xs text-txtsecondary">Sampler</span>
+          <select
+            class="px-2 py-1 rounded border border-gray-200 dark:border-white/10 bg-surface focus:outline-none focus:ring-2 focus:ring-primary"
+            bind:value={$sdSamplerStore}
+          >
+            <option value="">Default</option>
+            <option value="euler_a">euler_a</option>
+            <option value="euler">euler</option>
+            <option value="heun">heun</option>
+            <option value="dpm2">dpm2</option>
+            <option value="dpmpp2s_a">dpmpp2s_a</option>
+            <option value="dpmpp2m">dpmpp2m</option>
+            <option value="dpmpp2mv2">dpmpp2mv2</option>
+            <option value="ipndm">ipndm</option>
+            <option value="ipndm_v">ipndm_v</option>
+            <option value="lcm">lcm</option>
+            <option value="ddim_trailing">ddim_trailing</option>
+            <option value="tcd">tcd</option>
+          </select>
+        </label>
+        <label class="flex flex-col gap-1">
+          <span class="text-xs text-txtsecondary">Scheduler</span>
+          <select
+            class="px-2 py-1 rounded border border-gray-200 dark:border-white/10 bg-surface focus:outline-none focus:ring-2 focus:ring-primary"
+            bind:value={$sdSchedulerStore}
+          >
+            <option value="">Auto for model</option>
+            <option value="discrete">discrete</option>
+            <option value="karras">karras</option>
+            <option value="exponential">exponential</option>
+            <option value="ays">ays</option>
+            <option value="gits">gits</option>
+          </select>
+        </label>
+      </div>
+
+      <label class="flex flex-col gap-1 mb-3">
+        <span class="text-xs text-txtsecondary">Negative Prompt</span>
+        <textarea
+          class="px-2 py-1 rounded border border-gray-200 dark:border-white/10 bg-surface focus:outline-none focus:ring-2 focus:ring-primary resize-y text-sm"
+          bind:value={$sdNegativePromptStore}
+          rows="2"
+          placeholder="Elements to avoid..."
+        ></textarea>
+      </label>
+
+      <!-- LoRA Selection -->
+      <div>
+        <span class="text-xs text-txtsecondary block mb-1">LoRAs</span>
+        <div class="flex items-center gap-2 mb-2">
+          <button
+            class="px-3 py-1.5 text-sm rounded border border-gray-200 dark:border-white/10 bg-surface hover:bg-secondary-hover transition-colors disabled:opacity-50"
+            onclick={loadLoras}
+            disabled={!$selectedModelStore || isLoadingLoras}
+          >
+            {isLoadingLoras ? "Loading..." : lorasLoaded ? "Reload LoRAs" : "Load LoRAs"}
+          </button>
+          {#if lorasLoaded && availableLoras.length > 0}
+            <select
+              class="flex-1 px-2 py-1.5 text-sm rounded border border-gray-200 dark:border-white/10 bg-surface focus:outline-none focus:ring-2 focus:ring-primary"
+              onchange={addLora}
+            >
+              <option value="">Add a LoRA...</option>
+              {#each availableLoras.filter((l) => !selectedLoras.some((s) => s.path === l.path)) as lora}
+                <option value={lora.path}>{lora.name}</option>
+              {/each}
+            </select>
+          {/if}
+        </div>
+        {#if loraError}
+          <p class="text-xs text-red-500 mb-1">{loraError}</p>
+        {/if}
+        {#if lorasLoaded && availableLoras.length === 0}
+          <p class="text-xs text-txtsecondary">No LoRAs available</p>
+        {/if}
+        {#if selectedLoras.length > 0}
+          <div class="flex flex-col gap-1.5">
+            {#each selectedLoras as lora}
+              <div class="flex items-center gap-2 text-sm">
+                <span class="flex-1 truncate">{getLoraName(lora.path)}</span>
+                <input
+                  type="number"
+                  class="w-20 px-1.5 py-1 text-xs rounded border border-gray-200 dark:border-white/10 bg-surface focus:outline-none focus:ring-1 focus:ring-primary"
+                  value={lora.multiplier}
+                  oninput={(e) => updateLoraMultiplier(lora.path, parseFloat((e.target as HTMLInputElement).value) || 1)}
+                  min="0"
+                  max="2"
+                  step="0.1"
+                />
+                <button
+                  class="px-1.5 py-0.5 text-xs rounded border border-gray-200 dark:border-white/10 hover:bg-red-500 hover:text-white hover:border-red-500 transition-colors"
+                  onclick={() => removeLora(lora.path)}
+                  aria-label="Remove LoRA"
+                >
+                  x
+                </button>
+              </div>
+            {/each}
+          </div>
+        {/if}
+      </div>
+    </div>
+  {/if}
+
   <!-- Empty state for no models configured -->
   {#if !hasModels}
     <div class="flex-1 flex items-center justify-center text-txtsecondary">
@@ -143,22 +402,50 @@
           <p class="font-medium">Error</p>
           <p class="text-sm mt-1">{error}</p>
         </div>
-      {:else if generatedImage}
+      {:else if generatedImages.length > 1}
+        <!-- Grid for multiple images (batch) -->
+        <div class="grid grid-cols-2 gap-2 p-2 w-full h-full overflow-auto">
+          {#each generatedImages as img, i}
+            <div class="relative flex items-center justify-center">
+              <button
+                class="p-0 border-0 bg-transparent cursor-pointer"
+                onclick={() => openFullscreen(i)}
+                aria-label="View fullscreen"
+              >
+                <img
+                  src={img}
+                  alt="AI generated content {i + 1}"
+                  class="max-w-full max-h-full object-contain hover:opacity-90 transition-opacity"
+                />
+              </button>
+              <button
+                class="absolute bottom-2 right-2 p-1.5 bg-black/60 hover:bg-black/80 text-white rounded-full transition-colors"
+                onclick={(e) => { e.stopPropagation(); downloadImage(i); }}
+                aria-label="Download image"
+              >
+                <svg class="w-4 h-4" fill="none" stroke="currentColor" viewBox="0 0 24 24">
+                  <path stroke-linecap="round" stroke-linejoin="round" stroke-width="2" d="M4 16v1a3 3 0 003 3h10a3 3 0 003-3v-1m-4-4l-4 4m0 0l-4-4m4 4V4"></path>
+                </svg>
+              </button>
+            </div>
+          {/each}
+        </div>
+      {:else if generatedImages.length === 1}
         <div class="relative max-w-full max-h-full flex items-center justify-center">
           <button
             class="p-0 border-0 bg-transparent cursor-pointer"
-            onclick={openFullscreen}
+            onclick={() => openFullscreen(0)}
             aria-label="View fullscreen"
           >
             <img
-              src={generatedImage}
+              src={generatedImages[0]}
               alt="AI generated content"
               class="max-w-full max-h-full object-contain hover:opacity-90 transition-opacity"
             />
           </button>
           <button
             class="absolute bottom-2 right-2 p-2 bg-black/60 hover:bg-black/80 text-white rounded-full transition-colors"
-            onclick={(e) => { e.stopPropagation(); downloadImage(); }}
+            onclick={(e) => { e.stopPropagation(); downloadImage(0); }}
             aria-label="Download image"
           >
             <svg class="w-5 h-5" fill="none" stroke="currentColor" viewBox="0 0 24 24">
@@ -198,7 +485,7 @@
           <button
             class="btn flex-1 md:flex-none"
             onclick={clearImage}
-            disabled={!generatedImage && !error && !prompt.trim()}
+            disabled={generatedImages.length === 0 && !error && !prompt.trim()}
           >
             Clear
           </button>
@@ -209,7 +496,7 @@
 </div>
 
 <!-- Fullscreen dialog -->
-{#if showFullscreen && generatedImage}
+{#if showFullscreen && generatedImages[fullscreenIndex]}
   <div
     class="fixed inset-0 bg-black/90 z-50 flex items-center justify-center p-4"
     onclick={(e) => closeFullscreen(e)}
@@ -226,7 +513,7 @@
       ×
     </button>
     <img
-      src={generatedImage}
+      src={generatedImages[fullscreenIndex]}
       alt="AI generated content"
       class="max-w-full max-h-full object-contain pointer-events-none"
     />

ui-svelte/src/lib/sdApi.ts

@@ -0,0 +1,39 @@
+import type { SdApiTxt2ImgRequest, SdApiResponse, SdApiLora } from "./types";
+
+export async function generateSdImage(
+  request: SdApiTxt2ImgRequest,
+  signal?: AbortSignal
+): Promise<SdApiResponse> {
+  const response = await fetch("/sdapi/v1/txt2img", {
+    method: "POST",
+    headers: {
+      "Content-Type": "application/json",
+    },
+    body: JSON.stringify(request),
+    signal,
+  });
+
+  if (!response.ok) {
+    const errorText = await response.text();
+    throw new Error(`SDAPI error: ${response.status} - ${errorText}`);
+  }
+
+  return response.json();
+}
+
+export async function fetchSdLoras(
+  model: string,
+  signal?: AbortSignal
+): Promise<SdApiLora[]> {
+  const response = await fetch(
+    `/sdapi/v1/loras?model=${encodeURIComponent(model)}`,
+    { signal }
+  );
+
+  if (!response.ok) {
+    const errorText = await response.text();
+    throw new Error(`SDAPI loras error: ${response.status} - ${errorText}`);
+  }
+
+  return response.json();
+}

ui-svelte/src/lib/types.ts

@@ -115,6 +115,40 @@ export interface ImageGenerationResponse {
   }>;
 }
 
+// SDAPI types (stable-diffusion.cpp)
+export type ImageApiMode = "openai" | "sdapi";
+
+export interface SdApiLora {
+  name: string;
+  path: string;
+}
+
+export interface SdApiLoraRef {
+  path: string;
+  multiplier: number;
+}
+
+export interface SdApiTxt2ImgRequest {
+  model?: string;
+  prompt: string;
+  negative_prompt?: string;
+  width?: number;
+  height?: number;
+  steps?: number;
+  cfg_scale?: number;
+  seed?: number;
+  batch_size?: number;
+  sampler_name?: string;
+  scheduler?: string;
+  lora?: SdApiLoraRef[];
+}
+
+export interface SdApiResponse {
+  images: string[];
+  parameters: Record<string, unknown>;
+  info: string;
+}
+
 export interface AudioTranscriptionRequest {
   file: File;
   model: string;

ui-svelte/src/stores/api.ts

@@ -62,7 +62,7 @@ export function enableAPIEvents(enabled: boolean): void {
             const newModels = JSON.parse(message.data) as Model[];
             // Sort models by name and id
             newModels.sort((a, b) => {
-              return (a.name + a.id).localeCompare(b.name + b.id);
+              return (a.name + a.id).localeCompare(b.name + b.id, undefined, { numeric : true} );
             });
             models.set(newModels);
             break;

ui-svelte/vite.config.ts

@@ -32,6 +32,7 @@ export default defineConfig({
       "/upstream": "http://localhost:8080",
       "/unload": "http://localhost:8080",
       "/v1": "http://localhost:8080",
+      "/sdapi": "http://localhost:8080",
     },
   },
 });