Properly strip profile name slug from models fixes (#62)

The profile slug in a model name, `profile:model`, is specific to
llama-swap. This strips `profile:` out of the model name request so
upstreams that expect just `model` work and do not require knowing about
the profile slug.

.github/workflows/containers.yml

@@ -0,0 +1,45 @@
+name: Build Containers
+
+on:
+  # time has no specific meaning, trying to time it after
+  # the llama.cpp daily packages are published
+  # https://github.com/ggml-org/llama.cpp/blob/master/.github/workflows/docker.yml
+  schedule:
+    - cron: "37 5 * * *"
+
+  # Allows manual triggering of the workflow
+  workflow_dispatch:
+
+jobs:
+  build-and-push:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        platform: [intel, cuda, vulkan, cpu, musa]
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Log in to GitHub Container Registry
+        uses: docker/login-action@v2
+        with:
+          registry: ghcr.io
+          username: ${{ github.actor }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Run build-container
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        run: ./docker/build-container.sh ${{ matrix.platform }} true
+
+  # note make sure mostlygeek/llama-swap has admin rights to the llama-swap package
+  # see: https://github.com/actions/delete-package-versions/issues/74
+  delete-untagged-containers:
+    needs: build-and-push
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/delete-package-versions@v5
+        with:
+          package-name: 'llama-swap'
+          package-type: 'container'
+          delete-only-untagged-versions: 'true'

.github/workflows/release.yml

@@ -5,6 +5,9 @@ on:
     tags:
       - '*'
 
+  # Allows manual triggering of the workflow
+  workflow_dispatch:
+
 permissions:
   contents: write
 
@@ -30,4 +33,4 @@ jobs:
           version: '~> v2'
           args: release --clean
         env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

.gitignore

@@ -2,4 +2,5 @@
 .env
 build/
 dist/
-.vscode
+.vscode
+.DS_Store

.goreleaser.yaml

@@ -6,6 +6,13 @@ builds:
     goos:
       - linux
       - darwin
+      - freebsd
+      - windows
     goarch:
       - amd64
-      - arm64
+      - arm64
+    ignore:
+      - goos: freebsd
+        goarch: arm64
+      - goos: windows
+        goarch: arm64

Makefile

@@ -2,6 +2,16 @@
 APP_NAME = llama-swap
 BUILD_DIR = build
 
+# Get the current Git hash
+GIT_HASH := $(shell git rev-parse --short HEAD)
+ifneq ($(shell git status --porcelain),)
+    # There are untracked changes
+    GIT_HASH := $(GIT_HASH)+
+endif
+
+# Capture the current build date in RFC3339 format
+BUILD_DATE := $(shell date -u +"%Y-%m-%dT%H:%M:%SZ")
+
 # Default target: Builds binaries for both OSX and Linux
 all: mac linux simple-responder
 
@@ -18,12 +28,17 @@ test-all:
 # Build OSX binary
 mac:
 	@echo "Building Mac binary..."
-	GOOS=darwin GOARCH=arm64 go build -o $(BUILD_DIR)/$(APP_NAME)-darwin-arm64
+	GOOS=darwin 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)-darwin-arm64
 
 # Build Linux binary
 linux:
 	@echo "Building Linux binary..."
-	GOOS=linux GOARCH=amd64 go build -o $(BUILD_DIR)/$(APP_NAME)-linux-amd64
+	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
+
+# Build Windows binary
+windows:
+	@echo "Building Windows binary..."
+	GOOS=windows 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)-windows-amd64.exe
 
 # for testing proxy.Process
 simple-responder:
@@ -35,5 +50,19 @@ simple-responder:
 $(BUILD_DIR):
 	mkdir -p $(BUILD_DIR)
 
+# Create a new release tag
+release:
+	@echo "Checking for unstaged changes..."
+	@if [ -n "$(shell git status --porcelain)" ]; then \
+		echo "Error: There are unstaged changes. Please commit or stash your changes before creating a release tag." >&2; \
+		exit 1; \
+	fi
+
+# Get the highest tag in v{number} format, increment it, and create a new tag
+	@highest_tag=$$(git tag --sort=-v:refname | grep -E '^v[0-9]+$$' | head -n 1 || echo "v0"); \
+	new_tag="v$$(( $${highest_tag#v} + 1 ))"; \
+	echo "tagging new version: $$new_tag"; \
+	git tag "$$new_tag";
+
 # Phony targets
-.PHONY: all clean osx linux
+.PHONY: all clean mac linux windows simple-responder

README.md

@@ -1,42 +1,69 @@
-# llama-swap
-
 ![llama-swap header image](header.jpeg)
 
-# Introduction
-llama-swap is an OpenAI API compatible server that gives you complete control over how you use your hardware. It automatically swaps to the configuration of your choice for serving a model. Since [llama.cpp's server](https://github.com/ggerganov/llama.cpp/tree/master/examples/server) can't swap models, let's swap the server instead!
+# llama-swap
 
-Features:
+llama-swap is a light weight, transparent proxy server that provides automatic model swapping to llama.cpp's server.
+
+Written in golang, it is very easy to install (single binary with no dependancies) and configure (single yaml file). To get started, download a pre-built binary or use the provided docker images.
+
+## Features:
 
 - ✅ Easy to deploy: single binary with no dependencies
-- ✅ Single yaml configuration file
+- ✅ Easy to config: single yaml file
 - ✅ On-demand model switching
 - ✅ Full control over server settings per model
-- ✅ OpenAI API support (`v1/completions` and `v1/chat/completions`)
-- ✅ Multiple GPU support
-- ✅ Run multiple models at once with `profiles`
+- ✅ OpenAI API supported endpoints:
+  - `v1/completions`
+  - `v1/chat/completions`
+  - `v1/embeddings`
+  - `v1/rerank`
+  - `v1/audio/speech` ([#36](https://github.com/mostlygeek/llama-swap/issues/36))
+- ✅ Run multiple models at once with `profiles` ([docs](https://github.com/mostlygeek/llama-swap/issues/53#issuecomment-2660761741))
 - ✅ Remote log monitoring at `/log`
-- ✅ Automatic unloading of models from GPUs after timeout
+- ✅ Direct access to upstream HTTP server via `/upstream/:model_id` ([demo](https://github.com/mostlygeek/llama-swap/pull/31))
+- ✅ Manually unload models via `/unload` endpoint ([#58](https://github.com/mostlygeek/llama-swap/issues/58))
+- ✅ Automatic unloading of models after timeout by setting a `ttl`
+- ✅ Use any local OpenAI compatible server (llama.cpp, vllm, tabbyAPI, etc)
+- ✅ Docker and Podman support
 
-## Releases
+## How does llama-swap work?
 
-Builds for Linux and OSX are available on the [Releases](https://github.com/mostlygeek/llama-swap/releases) page.
+When a request is made to an OpenAI compatible endpoint, lama-swap will extract the `model` value and load the appropriate server configuration to serve it. If the wrong upstream server is running, it will be replaced with the correct one. This is where the "swap" part comes in. The upstream server is automatically swapped to the correct one to serve the request.
 
-### Building from source
-
-1. Install golang for your system
-1. `git clone git@github.com:mostlygeek/llama-swap.git`
-1. `make clean all`
-1. Binaries will be in `build/` subdirectory
+In the most basic configuration llama-swap handles one model at a time. For more advanced use cases, the `profiles` feature can load multiple models at the same time. You have complete control over how your system resources are used.
 
 ## config.yaml
 
 llama-swap's configuration is purposefully simple.
 
+```yaml
+models:
+  "qwen2.5":
+    proxy: "http://127.0.0.1:9999"
+    cmd: >
+      /app/llama-server
+      -hf bartowski/Qwen2.5-0.5B-Instruct-GGUF:Q4_K_M
+      --port 9999
+
+  "smollm2":
+    proxy: "http://127.0.0.1:9999"
+    cmd: >
+      /app/llama-server
+      -hf bartowski/SmolLM2-135M-Instruct-GGUF:Q4_K_M
+      --port 9999
+```
+
+<details>
+<summary>But also very powerful ...</summary>
+
 ```yaml
 # Seconds to wait for llama.cpp to load and be ready to serve requests
 # Default (and minimum) is 15 seconds
 healthCheckTimeout: 60
 
+# Write HTTP logs (useful for troubleshooting), defaults to false
+logRequests: true
+
 # define valid model values and the upstream server start
 models:
   "llama":
@@ -47,8 +74,8 @@ models:
 
     # aliases names to use this model for
     aliases:
-    - "gpt-4o-mini"
-    - "gpt-3.5-turbo"
+      - "gpt-4o-mini"
+      - "gpt-3.5-turbo"
 
     # check this path for an HTTP 200 OK before serving requests
     # default: /health to match llama.cpp
@@ -72,6 +99,21 @@ models:
       --model path/to/Qwen2.5-1.5B-Instruct-Q4_K_M.gguf
     proxy: http://127.0.0.1:8999
 
+  # unlisted models do not show up in /v1/models or /upstream lists
+  # but they can still be requested as normal
+  "qwen-unlisted":
+    unlisted: true
+    cmd: llama-server --port 9999 -m Llama-3.2-1B-Instruct-Q4_K_M.gguf -ngl 0
+
+  # Docker Support (v26.1.4+ required!)
+  "docker-llama":
+    proxy: "http://127.0.0.1:9790"
+    cmd: >
+      docker run --name dockertest
+      --init --rm -p 9790:8080 -v /mnt/nvme/models:/models
+      ghcr.io/ggerganov/llama.cpp:server
+      --model '/models/Qwen2.5-Coder-0.5B-Instruct-Q4_K_M.gguf'
+
 # profiles make it easy to managing multi model (and gpu) configurations.
 #
 # Tips:
@@ -84,15 +126,83 @@ profiles:
     - "llama"
 ```
 
-More [examples](examples/README.md) are available for different use cases.
+### Use Case Examples
 
-## Installation
+- [config.example.yaml](config.example.yaml) includes example for supporting `v1/embeddings` and `v1/rerank` endpoints
+- [Speculative Decoding](examples/speculative-decoding/README.md) - using a small draft model can increase inference speeds from 20% to 40%. This example includes a configurations Qwen2.5-Coder-32B (2.5x increase) and Llama-3.1-70B (1.4x increase) in the best cases.
+- [Optimizing Code Generation](examples/benchmark-snakegame/README.md) - find the optimal settings for your machine. This example demonstrates defining multiple configurations and testing which one is fastest.
+- [Restart on Config Change](examples/restart-on-config-change/README.md) - automatically restart llama-swap when trying out different configurations.
+
+## Configuration
+
+llama-s
+
+</details>
+
+## Docker Install ([download images](https://github.com/mostlygeek/llama-swap/pkgs/container/llama-swap))
+
+Docker is the quickest way to try out llama-swap:
+
+```
+# use CPU inference
+$ docker run -it --rm -p 9292:8080 ghcr.io/mostlygeek/llama-swap:cpu
+
+
+# qwen2.5 0.5B
+$ curl -s http://localhost:9292/v1/chat/completions \
+    -H "Content-Type: application/json" \
+    -H "Authorization: Bearer no-key" \
+    -d '{"model":"qwen2.5","messages": [{"role": "user","content": "tell me a joke"}]}' | \
+    jq -r '.choices[0].message.content'
+
+
+# SmolLM2 135M
+$ curl -s http://localhost:9292/v1/chat/completions \
+    -H "Content-Type: application/json" \
+    -H "Authorization: Bearer no-key" \
+    -d '{"model":"smollm2","messages": [{"role": "user","content": "tell me a joke"}]}' | \
+    jq -r '.choices[0].message.content'
+```
+
+<details>
+<summary>Docker images are nightly ...</summary>
+
+They include:
+
+- `ghcr.io/mostlygeek/llama-swap:cpu`
+- `ghcr.io/mostlygeek/llama-swap:cuda`
+- `ghcr.io/mostlygeek/llama-swap:intel`
+- `ghcr.io/mostlygeek/llama-swap:vulkan`
+- ROCm disabled until fixed in llama.cpp container
+
+Specific versions are also available and are tagged with the llama-swap, architecture and llama.cpp versions. For example: `ghcr.io/mostlygeek/llama-swap:v89-cuda-b4716`
+
+Beyond the demo you will likely want to run the containers with your downloaded models and custom configuration.
+
+```
+$ docker run -it --rm --runtime nvidia -p 9292:8080 \
+  -v /path/to/models:/models \
+  -v /path/to/custom/config.yaml:/app/config.yaml \
+  ghcr.io/mostlygeek/llama-swap:cuda
+```
+
+</details>
+
+## Bare metal Install ([download](https://github.com/mostlygeek/llama-swap/releases))
+
+Pre-built binaries are available for Linux, FreeBSD and Darwin (OSX). These are automatically published and are likely a few hours ahead of the docker releases. The baremetal install works with any OpenAI compatible server, not just llama-server.
 
 1. Create a configuration file, see [config.example.yaml](config.example.yaml)
 1. Download a [release](https://github.com/mostlygeek/llama-swap/releases) appropriate for your OS and architecture.
-    * _Note: Windows currently untested._
 1. Run the binary with `llama-swap --config path/to/config.yaml`
 
+### Building from source
+
+1. Install golang for your system
+1. `git clone git@github.com:mostlygeek/llama-swap.git`
+1. `make clean all`
+1. Binaries will be in `build/` subdirectory
+
 ## Monitoring Logs
 
 Open the `http://<host>/logs` with your browser to get a web interface with streaming logs.
@@ -113,11 +223,18 @@ curl -Ns http://host/logs/stream | grep 'eval time'
 curl -Ns 'http://host/logs/stream?no-history'
 ```
 
+## Do I need to use llama.cpp's server (llama-server)?
+
+Any OpenAI compatible server would work. llama-swap was originally designed for llama-server and it is the best supported.
+
+For Python based inference servers like vllm or tabbyAPI it is recommended to run them via podman or docker. This provides clean environment isolation as well as responding correctly to `SIGTERM` signals to shutdown.
+
 ## Systemd Unit Files
 
 Use this unit file to start llama-swap on boot. This is only tested on Ubuntu.
 
 `/etc/systemd/system/llama-swap.service`
+
 ```
 [Unit]
 Description=llama-swap
@@ -137,3 +254,11 @@ StartLimitInterval=30
 [Install]
 WantedBy=multi-user.target
 ```
+
+## Star History
+
+<picture>
+   <source media="(prefers-color-scheme: dark)" srcset="https://api.star-history.com/svg?repos=mostlygeek/llama-swap&type=Date&theme=dark" />
+   <source media="(prefers-color-scheme: light)" srcset="https://api.star-history.com/svg?repos=mostlygeek/llama-swap&type=Date" />
+   <img alt="Star History Chart" src="https://api.star-history.com/svg?repos=mostlygeek/llama-swap&type=Date" />
+</picture>

config.example.yaml

@@ -2,6 +2,9 @@
 # Default (and minimum): 15 seconds
 healthCheckTimeout: 15
 
+# Log HTTP requests helpful for troubleshoot, defaults to False
+logRequests: true
+
 models:
   "llama":
     cmd: >
@@ -26,6 +29,39 @@ models:
     aliases:
     - gpt-3.5-turbo
 
+  # Embedding example with Nomic
+  # https://huggingface.co/nomic-ai/nomic-embed-text-v1.5-GGUF
+  "nomic":
+    proxy: http://127.0.0.1:9005
+    cmd: >
+      models/llama-server-osx --port 9005
+      -m models/nomic-embed-text-v1.5.Q8_0.gguf
+      --ctx-size 8192
+      --batch-size 8192
+      --rope-scaling yarn
+      --rope-freq-scale 0.75
+      -ngl 99
+      --embeddings
+
+  # Reranking example with bge-reranker
+  # https://huggingface.co/gpustack/bge-reranker-v2-m3-GGUF
+  "bge-reranker":
+    proxy: http://127.0.0.1:9006
+    cmd: >
+      models/llama-server-osx --port 9006
+      -m models/bge-reranker-v2-m3-Q4_K_M.gguf
+      --ctx-size 8192
+      --reranking
+
+  # Docker Support (v26.1.4+ required!)
+  "dockertest":
+    proxy: "http://127.0.0.1:9790"
+    cmd: >
+      docker run --name dockertest
+      --init --rm -p 9790:8080 -v /mnt/nvme/models:/models
+      ghcr.io/ggerganov/llama.cpp:server
+      --model '/models/Qwen2.5-Coder-0.5B-Instruct-Q4_K_M.gguf'
+
   "simple":
     # example of setting environment variables
     env:
@@ -33,6 +69,7 @@ models:
       - env1=hello
     cmd: build/simple-responder --port 8999
     proxy: http://127.0.0.1:8999
+    unlisted: true
 
     # use "none" to skip check. Caution this may cause some requests to fail
     # until the upstream server is ready for traffic
@@ -42,9 +79,11 @@ models:
   "broken":
     cmd: models/llama-server-osx --port 8999 -m models/doesnotexist.gguf
     proxy: http://127.0.0.1:8999
+    unlisted: true
   "broken_timeout":
     cmd: models/llama-server-osx --port 8999 -m models/qwen2.5-0.5b-instruct-q8_0.gguf
     proxy: http://127.0.0.1:9000
+    unlisted: true
 
 # creating a coding profile with models for code generation and general questions
 profiles:

docker/build-container.sh

@@ -0,0 +1,49 @@
+#!/bin/bash
+
+cd $(dirname "$0")
+
+ARCH=$1
+PUSH_IMAGES=${2:-false}
+
+# List of allowed architectures
+ALLOWED_ARCHS=("intel" "vulkan" "musa" "cuda" "cpu")
+
+# Check if ARCH is in the allowed list
+if [[ ! " ${ALLOWED_ARCHS[@]} " =~ " ${ARCH} " ]]; then
+  echo "Error: ARCH must be one of the following: ${ALLOWED_ARCHS[@]}"
+  exit 1
+fi
+
+# Check if GITHUB_TOKEN is set and not empty
+if [[ -z "$GITHUB_TOKEN" ]]; then
+  echo "Error: GITHUB_TOKEN is not set or is empty."
+  exit 1
+fi
+
+# the most recent llama-swap tag
+# have to strip out the 'v' due to .tar.gz file naming
+LS_VER=$(curl -s https://api.github.com/repos/mostlygeek/llama-swap/releases/latest | jq -r .tag_name | sed 's/v//')
+
+if [ "$ARCH" == "cpu" ]; then
+    # cpu only containers just use the latest available
+    CONTAINER_LATEST="ghcr.io/mostlygeek/llama-swap:cpu"
+    echo "Building ${CONTAINER_LATEST} $LS_VER"
+    docker build -f llama-swap.Containerfile --build-arg BASE_TAG=server --build-arg LS_VER=${LS_VER} -t ${CONTAINER_LATEST} .
+    if [ "$PUSH_IMAGES" == "true" ]; then
+      docker push ${CONTAINER_LATEST}
+    fi
+else
+    LCPP_TAG=$(curl -s -H "Authorization: Bearer $GITHUB_TOKEN" \
+        "https://api.github.com/users/ggml-org/packages/container/llama.cpp/versions" \
+        | jq -r --arg arch "$ARCH" '.[] | select(.metadata.container.tags[] | startswith("server-\($arch)")) | .metadata.container.tags[]' \
+        | sort -r | head -n1 | awk -F '-' '{print $3}')
+
+    CONTAINER_TAG="ghcr.io/mostlygeek/llama-swap:v${LS_VER}-${ARCH}-${LCPP_TAG}"
+    CONTAINER_LATEST="ghcr.io/mostlygeek/llama-swap:${ARCH}"
+    echo "Building ${CONTAINER_TAG} $LS_VER"
+    docker build -f llama-swap.Containerfile --build-arg BASE_TAG=server-${ARCH}-${LCPP_TAG} --build-arg LS_VER=${LS_VER} -t ${CONTAINER_TAG} -t ${CONTAINER_LATEST} .
+    if [ "$PUSH_IMAGES" == "true" ]; then
+      docker push ${CONTAINER_TAG}
+      docker push ${CONTAINER_LATEST}
+    fi
+fi

docker/config.example.yaml

@@ -0,0 +1,17 @@
+healthCheckTimeout: 300
+logRequests: true
+
+models:
+  "qwen2.5":
+    proxy: "http://127.0.0.1:9999"
+    cmd: >
+      /app/llama-server
+      -hf bartowski/Qwen2.5-0.5B-Instruct-GGUF:Q4_K_M
+      --port 9999
+
+  "smollm2":
+    proxy: "http://127.0.0.1:9999"
+    cmd: >
+      /app/llama-server
+      -hf bartowski/SmolLM2-135M-Instruct-GGUF:Q4_K_M
+      --port 9999

docker/llama-swap.Containerfile

@@ -0,0 +1,16 @@
+ARG BASE_TAG=server-cuda
+FROM ghcr.io/ggml-org/llama.cpp:${BASE_TAG}
+
+# has to be after the FROM
+ARG LS_VER=89
+
+WORKDIR /app
+RUN \
+    curl -LO https://github.com/mostlygeek/llama-swap/releases/download/v"${LS_VER}"/llama-swap_"${LS_VER}"_linux_amd64.tar.gz && \
+    tar -zxf llama-swap_"${LS_VER}"_linux_amd64.tar.gz && \
+    rm llama-swap_"${LS_VER}"_linux_amd64.tar.gz
+
+COPY config.example.yaml /app/config.yaml
+
+HEALTHCHECK CMD curl -f http://localhost:8080/ || exit 1
+ENTRYPOINT [ "/app/llama-swap", "-config", "/app/config.yaml" ]

examples/restart-on-config-change/README.md

@@ -0,0 +1,51 @@
+# Restart llama-swap on config change
+
+Sometimes editing the configuration file can take a bit of trail and error to get a model configuration tuned just right. The `watch-and-restart.sh` script can be used to watch `config.yaml` for changes and restart `llama-swap` when it detects a change.
+
+```bash
+#!/bin/bash
+#
+# A simple watch and restart llama-swap when its configuration
+# file changes. Useful for trying out configuration changes
+# without manually restarting the server each time.
+if [ -z "$1" ]; then
+    echo "Usage: $0 <path to config.yaml>"
+    exit 1
+fi
+
+while true; do
+    # Start the process again
+    ./llama-swap-linux-amd64 -config $1 -listen :1867 &
+    PID=$!
+    echo "Started llama-swap with PID $PID"
+
+    # Wait for modifications in the specified directory or file
+    inotifywait -e modify "$1"
+
+    # Check if process exists before sending signal
+    if kill -0 $PID 2>/dev/null; then
+        echo "Sending SIGTERM to $PID"
+        kill -SIGTERM $PID
+        wait $PID
+    else
+        echo "Process $PID no longer exists"
+    fi
+    sleep 1
+done
+```
+
+## Usage and output example
+
+```bash
+$ ./watch-and-restart.sh config.yaml
+Started llama-swap with PID 495455
+Setting up watches.
+Watches established.
+llama-swap listening on :1867
+Sending SIGTERM to 495455
+Shutting down llama-swap
+Started llama-swap with PID 495486
+Setting up watches.
+Watches established.
+llama-swap listening on :1867
+```

go.mod

@@ -29,12 +29,16 @@ require (
 	github.com/modern-go/reflect2 v1.0.2 // indirect
 	github.com/pelletier/go-toml/v2 v2.2.2 // indirect
 	github.com/pmezard/go-difflib v1.0.0 // indirect
+	github.com/tidwall/gjson v1.18.0 // indirect
+	github.com/tidwall/match v1.1.1 // indirect
+	github.com/tidwall/pretty v1.2.1 // indirect
+	github.com/tidwall/sjson v1.2.5 // indirect
 	github.com/twitchyliquid64/golang-asm v0.15.1 // indirect
 	github.com/ugorji/go/codec v1.2.12 // indirect
 	golang.org/x/arch v0.8.0 // indirect
-	golang.org/x/crypto v0.23.0 // indirect
-	golang.org/x/net v0.25.0 // indirect
-	golang.org/x/sys v0.20.0 // indirect
-	golang.org/x/text v0.15.0 // indirect
+	golang.org/x/crypto v0.31.0 // indirect
+	golang.org/x/net v0.33.0 // indirect
+	golang.org/x/sys v0.28.0 // indirect
+	golang.org/x/text v0.21.0 // indirect
 	google.golang.org/protobuf v1.34.1 // indirect
 )

go.sum

@@ -57,6 +57,16 @@ github.com/stretchr/testify v1.8.1/go.mod h1:w2LPCIKwWwSfY2zedu0+kehJoqGctiVI29o
 github.com/stretchr/testify v1.8.4/go.mod h1:sz/lmYIOXD/1dqDmKjjqLyZ2RngseejIcXlSw2iwfAo=
 github.com/stretchr/testify v1.9.0 h1:HtqpIVDClZ4nwg75+f6Lvsy/wHu+3BoSGCbBAcpTsTg=
 github.com/stretchr/testify v1.9.0/go.mod h1:r2ic/lqez/lEtzL7wO/rwa5dbSLXVDPFyf8C91i36aY=
+github.com/tidwall/gjson v1.14.2/go.mod h1:/wbyibRr2FHMks5tjHJ5F8dMZh3AcwJEMf5vlfC0lxk=
+github.com/tidwall/gjson v1.18.0 h1:FIDeeyB800efLX89e5a8Y0BNH+LOngJyGrIWxG2FKQY=
+github.com/tidwall/gjson v1.18.0/go.mod h1:/wbyibRr2FHMks5tjHJ5F8dMZh3AcwJEMf5vlfC0lxk=
+github.com/tidwall/match v1.1.1 h1:+Ho715JplO36QYgwN9PGYNhgZvoUSc9X2c80KVTi+GA=
+github.com/tidwall/match v1.1.1/go.mod h1:eRSPERbgtNPcGhD8UCthc6PmLEQXEWd3PRB5JTxsfmM=
+github.com/tidwall/pretty v1.2.0/go.mod h1:ITEVvHYasfjBbM0u2Pg8T2nJnzm8xPwvNhhsoaGGjNU=
+github.com/tidwall/pretty v1.2.1 h1:qjsOFOWWQl+N3RsoF5/ssm1pHmJJwhjlSbZ51I6wMl4=
+github.com/tidwall/pretty v1.2.1/go.mod h1:ITEVvHYasfjBbM0u2Pg8T2nJnzm8xPwvNhhsoaGGjNU=
+github.com/tidwall/sjson v1.2.5 h1:kLy8mja+1c9jlljvWTlSazM7cKDRfJuR/bOJhcY5NcY=
+github.com/tidwall/sjson v1.2.5/go.mod h1:Fvgq9kS/6ociJEDnK0Fk1cpYF4FIW6ZF7LAe+6jwd28=
 github.com/twitchyliquid64/golang-asm v0.15.1 h1:SU5vSMR7hnwNxj24w34ZyCi/FmDZTkS4MhqMhdFk5YI=
 github.com/twitchyliquid64/golang-asm v0.15.1/go.mod h1:a1lVb/DtPvCB8fslRZhAngC2+aY1QWCk3Cedj/Gdt08=
 github.com/ugorji/go/codec v1.2.12 h1:9LC83zGrHhuUA9l16C9AHXAqEV/2wBQ4nkvumAE65EE=
@@ -66,14 +76,22 @@ golang.org/x/arch v0.8.0 h1:3wRIsP3pM4yUptoR96otTUOXI367OS0+c9eeRi9doIc=
 golang.org/x/arch v0.8.0/go.mod h1:FEVrYAQjsQXMVJ1nsMoVVXPZg6p2JE2mx8psSWTDQys=
 golang.org/x/crypto v0.23.0 h1:dIJU/v2J8Mdglj/8rJ6UUOM3Zc9zLZxVZwwxMooUSAI=
 golang.org/x/crypto v0.23.0/go.mod h1:CKFgDieR+mRhux2Lsu27y0fO304Db0wZe70UKqHu0v8=
+golang.org/x/crypto v0.31.0 h1:ihbySMvVjLAeSH1IbfcRTkD/iNscyz8rGzjF/E5hV6U=
+golang.org/x/crypto v0.31.0/go.mod h1:kDsLvtWBEx7MV9tJOj9bnXsPbxwJQ6csT/x4KIN4Ssk=
 golang.org/x/net v0.25.0 h1:d/OCCoBEUq33pjydKrGQhw7IlUPI2Oylr+8qLx49kac=
 golang.org/x/net v0.25.0/go.mod h1:JkAGAh7GEvH74S6FOH42FLoXpXbE/aqXSrIQjXgsiwM=
+golang.org/x/net v0.33.0 h1:74SYHlV8BIgHIFC/LrYkOGIwL19eTYXQ5wc6TBuO36I=
+golang.org/x/net v0.33.0/go.mod h1:HXLR5J+9DxmrqMwG9qjGCxZ+zKXxBru04zlTvWlWuN4=
 golang.org/x/sys v0.5.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.6.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.20.0 h1:Od9JTbYCk261bKm4M/mw7AklTlFYIa0bIp9BgSm1S8Y=
 golang.org/x/sys v0.20.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
+golang.org/x/sys v0.28.0 h1:Fksou7UEQUWlKvIdsqzJmUmCX3cZuD2+P3XyyzwMhlA=
+golang.org/x/sys v0.28.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
 golang.org/x/text v0.15.0 h1:h1V/4gjBv8v9cjcR6+AR5+/cIYK5N/WAgiv4xlsEtAk=
 golang.org/x/text v0.15.0/go.mod h1:18ZOQIKpY8NJVqYksKHtTdi31H5itFRjB5/qKTNYzSU=
+golang.org/x/text v0.21.0 h1:zyQAAkrwaneQ066sspRyJaG9VNi/YJ1NfzcGB3hZ/qo=
+golang.org/x/text v0.21.0/go.mod h1:4IBbMaMmOPCJ8SecivzSH54+73PCFmPWxNTLm+vZkEQ=
 google.golang.org/protobuf v1.34.1 h1:9ddQBjfCyZPOHPUiPxpYESBLc+T8P3E+Vo4IbKZgFWg=
 google.golang.org/protobuf v1.34.1/go.mod h1:c6P6GXX6sHbq/GpV6MGZEdwhWPcYBgnhAHhKbcUYpos=
 gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405 h1:yhCVgyC4o1eVCa2tZl7eS0r+SDo693bJlVdllGtEeKM=

llama-swap.go

@@ -4,18 +4,30 @@ import (
 	"flag"
 	"fmt"
 	"os"
+	"os/signal"
+	"syscall"
 
 	"github.com/gin-gonic/gin"
 	"github.com/mostlygeek/llama-swap/proxy"
 )
 
+var version string = "0"
+var commit string = "abcd1234"
+var date = "unknown"
+
 func main() {
 	// Define a command-line flag for the port
 	configPath := flag.String("config", "config.yaml", "config file name")
 	listenStr := flag.String("listen", ":8080", "listen ip/port")
+	showVersion := flag.Bool("version", false, "show version of build")
 
 	flag.Parse() // Parse the command-line flags
 
+	if *showVersion {
+		fmt.Printf("version: %s (%s), built at %s\n", version, commit, date)
+		os.Exit(0)
+	}
+
 	config, err := proxy.LoadConfig(*configPath)
 	if err != nil {
 		fmt.Printf("Error loading config: %v\n", err)
@@ -29,6 +41,16 @@ func main() {
 	}
 
 	proxyManager := proxy.New(config)
+
+	sigChan := make(chan os.Signal, 1)
+	signal.Notify(sigChan, syscall.SIGINT, syscall.SIGTERM)
+	go func() {
+		<-sigChan
+		fmt.Println("Shutting down llama-swap")
+		proxyManager.Shutdown()
+		os.Exit(0)
+	}()
+
 	fmt.Println("llama-swap listening on " + *listenStr)
 	if err := proxyManager.Run(*listenStr); err != nil {
 		fmt.Printf("Server error: %v\n", err)

misc/simple-responder/simple-responder.go

@@ -12,12 +12,14 @@ import (
 	"time"
 
 	"github.com/gin-gonic/gin"
+	"github.com/tidwall/gjson"
 )
 
 func main() {
 	gin.SetMode(gin.TestMode)
 	// Define a command-line flag for the port
 	port := flag.String("port", "8080", "port to listen on")
+	expectedModel := flag.String("model", "TheExpectedModel", "model name to expect")
 
 	// Define a command-line flag for the response message
 	responseMessage := flag.String("respond", "hi", "message to respond with")
@@ -41,6 +43,25 @@ func main() {
 		c.String(200, *responseMessage)
 	})
 
+	// for issue #62 to check model name strips profile slug
+	// has to be one of the openAI API endpoints that llama-swap proxies
+	// curl http://localhost:8080/v1/audio/speech -d '{"model":"profile:TheExpectedModel"}'
+	r.POST("/v1/audio/speech", 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()
+		if modelName != *expectedModel {
+			c.JSON(http.StatusBadRequest, gin.H{"error": fmt.Sprintf("Invalid model: %s, expected: %s", modelName, *expectedModel)})
+			return
+		} else {
+			c.JSON(http.StatusOK, gin.H{"message": "ok"})
+		}
+	})
+
 	r.POST("/v1/completions", func(c *gin.Context) {
 		c.Header("Content-Type", "text/plain")
 		c.String(200, *responseMessage)

misc/test-rerank/README.md

@@ -0,0 +1,4 @@
+The rerank-test.json data is from https://github.com/ggerganov/llama.cpp/pull/9510
+
+To run it:
+> curl http://127.0.0.1:8080/v1/rerank -H "Content-Type: application/json" -d @reranker-test.json  -v | jq .

misc/test-rerank/reranker-test.json

@@ -0,0 +1,17 @@
+{
+  "model": "bge-reranker",
+  "query": "Organic skincare products for sensitive skin",
+  "top_n": 3,
+  "documents": [
+    "Organic skincare for sensitive skin with aloe vera and chamomile: Imagine the soothing embrace of nature with our organic skincare range, crafted specifically for sensitive skin. Infused with the calming properties of aloe vera and chamomile, each product provides gentle nourishment and protection. Say goodbye to irritation and hello to a glowing, healthy complexion.",
+    "New makeup trends focus on bold colors and innovative techniques: Step into the world of cutting-edge beauty with this seasons makeup trends. Bold, vibrant colors and groundbreaking techniques are redefining the art of makeup. From neon eyeliners to holographic highlighters, unleash your creativity and make a statement with every look.",
+    "Bio-Hautpflege für empfindliche Haut mit Aloe Vera und Kamille: Erleben Sie die wohltuende Wirkung unserer Bio-Hautpflege, speziell für empfindliche Haut entwickelt. Mit den beruhigenden Eigenschaften von Aloe Vera und Kamille pflegen und schützen unsere Produkte Ihre Haut auf natürliche Weise. Verabschieden Sie sich von Hautirritationen und genießen Sie einen strahlenden Teint.",
+    "Neue Make-up-Trends setzen auf kräftige Farben und innovative Techniken: Tauchen Sie ein in die Welt der modernen Schönheit mit den neuesten Make-up-Trends. Kräftige, lebendige Farben und innovative Techniken setzen neue Maßstäbe. Von auffälligen Eyelinern bis hin zu holografischen Highlightern – lassen Sie Ihrer Kreativität freien Lauf und setzen Sie jedes Mal ein Statement.",
+    "Cuidado de la piel orgánico para piel sensible con aloe vera y manzanilla: Descubre el poder de la naturaleza con nuestra línea de cuidado de la piel orgánico, diseñada especialmente para pieles sensibles. Enriquecidos con aloe vera y manzanilla, estos productos ofrecen una hidratación y protección suave. Despídete de las irritaciones y saluda a una piel radiante y saludable.",
+    "Las nuevas tendencias de maquillaje se centran en colores vivos y técnicas innovadoras: Entra en el fascinante mundo del maquillaje con las tendencias más actuales. Colores vivos y técnicas innovadoras están revolucionando el arte del maquillaje. Desde delineadores neón hasta iluminadores holográficos, desata tu creatividad y destaca en cada look.",
+    "针对敏感肌专门设计的天然有机护肤产品：体验由芦荟和洋甘菊提取物带来的自然呵护。我们的护肤产品特别为敏感肌设计，温和滋润，保护您的肌肤不受刺激。让您的肌肤告别不适，迎来健康光彩。",
+    "新的化妆趋势注重鲜艳的颜色和创新的技巧：进入化妆艺术的新纪元，本季的化妆趋势以大胆的颜色和创新的技巧为主。无论是霓虹眼线还是全息高光，每一款妆容都能让您脱颖而出，展现独特魅力。",
+    "敏感肌のために特別に設計された天然有機スキンケア製品: アロエベラとカモミールのやさしい力で、自然の抱擁を感じてください。敏感肌用に特別に設計された私たちのスキンケア製品は、肌に優しく栄養を与え、保護します。肌トラブルにさようなら、輝く健康な肌にこんにちは。",
+    "新しいメイクのトレンドは鮮やかな色と革新的な技術に焦点を当てています: 今シーズンのメイクアップトレンドは、大胆な色彩と革新的な技術に注目しています。ネオンアイライナーからホログラフィックハイライターまで、クリエイティビティを解き放ち、毎回ユニークなルックを演出しましょう。"
+  ]
+}

proxy/config.go

@@ -16,6 +16,7 @@ type ModelConfig struct {
 	Env           []string `yaml:"env"`
 	CheckEndpoint string   `yaml:"checkEndpoint"`
 	UnloadAfter   int      `yaml:"ttl"`
+	Unlisted      bool     `yaml:"unlisted"`
 }
 
 func (m *ModelConfig) SanitizedCommand() ([]string, error) {
@@ -24,6 +25,7 @@ func (m *ModelConfig) SanitizedCommand() ([]string, error) {
 
 type Config struct {
 	HealthCheckTimeout int                    `yaml:"healthCheckTimeout"`
+	LogRequests        bool                   `yaml:"logRequests"`
 	Models             map[string]ModelConfig `yaml:"models"`
 	Profiles           map[string][]string    `yaml:"profiles"`
 

proxy/html/index.html

@@ -0,0 +1,14 @@
+<!DOCTYPE html>
+<html lang="en">
+<head>
+    <meta charset="UTF-8">
+    <meta name="viewport" content="width=device-width, initial-scale=1.0">
+    <title>llama-swap</title>
+</head>
+<body>
+    <h1>llama-swap</h1>
+    <p>
+        <a href="/logs">view logs</a> | <a href="/upstream">configured models</a> | <a href="https://github.com/mostlygeek/llama-swap">github</a>
+    </p>
+</body>
+</html>

proxy/html/logs.html

@@ -12,42 +12,134 @@
             flex-direction: column;
             font-family: "Courier New", Courier, monospace;
         }
+        #log-controls {
+            margin: 0.5em;
+            display: flex;
+            align-items: center;
+            justify-content: space-between; /* Spaces out elements evenly */
+        }
+        #log-controls input {
+            flex: 1;
+        }
+        #log-controls input:focus {
+           outline: none; /* Ensures no outline is shown when the input is focused */
+        }
         #log-stream {
             flex: 1;
-            margin: 1em;
-            padding: 10px;
+            margin: 0.5em;
+            padding: 1em;
             background: #f4f4f4;
             overflow-y: auto;
             white-space: pre-wrap; /* Ensures line wrapping */
             word-wrap: break-word; /* Ensures long words wrap */
         }
+
+        .regex-error {
+            background-color: #ff0000 !important;
+        }
+
+        /* Dark mode styles */
+        @media (prefers-color-scheme: dark) {
+            body {
+                background-color: #333;
+                color: #fff;
+            }
+
+            #log-stream {
+                background: #444;
+                color: #fff;
+            }
+
+            #log-controls input {
+                background: #555;
+                color: #fff;
+                border: 1px solid #777;
+            }
+
+            #log-controls button {
+                background: #555;
+                color: #fff;
+                border: 1px solid #777;
+            }
+        }
     </style>
 </head>
 <body>
-    <pre id="log-stream">Waiting for logs...
-</pre>
-
+    <pre id="log-stream">Waiting for logs...</pre>
+    <div id="log-controls">
+        <input type="text" id="filter-input" placeholder="regex filter">
+        <button id="clear-button">clear</button>
+    </div>
     <script>
-        // Establish an EventSource connection to the SSE endpoint
-        if (typeof(EventSource) !== "undefined") {
-            const eventSource = new EventSource("/logs/streamSSE");
+        const logStream = document.getElementById('log-stream');
+        const filterInput = document.getElementById('filter-input');
+        var logData = "";
+        let regexFilter = null;
 
-            eventSource.onmessage = function(event) {
-                // Append the new log message to the <pre> element
-                const logStream = document.getElementById('log-stream');
+        function setupEventSource() {
+            if (typeof(EventSource) !== "undefined") {
+                const eventSource = new EventSource("/logs/streamSSE");
 
-                logStream.textContent += event.data;
+                eventSource.onmessage = function(event) {
+                    logData += event.data;
+                    render()
+                };
 
-                // Auto-scroll to the bottom
-                logStream.scrollTop = logStream.scrollHeight;
-            };
-
-            eventSource.onerror = function(err) {
-                console.error("EventSource failed:", err);
-            };
-        } else {
-            console.error("SSE not supported by this browser.");
+                eventSource.onerror = function(err) {
+                    logData = "EventSource failed: " + err.message;
+                };
+            } else {
+                logData = "SSE Not supported by this browser."
+            }
         }
+
+        // poor-ai's react  ¯\_(ツ)_/¯
+        function render() {
+            if (regexFilter) {
+                const lines = logData.split('\n');
+                const filteredLines = lines.filter(line => {
+                    return regexFilter === null || regexFilter.test(line);
+                });
+
+                if (filteredLines.length > 0) {
+                    logStream.textContent = filteredLines.join('\n') + '\n';
+                } else {
+                    logStream.textContent = "";
+                }
+            } else {
+                logStream.textContent = logData;
+            }
+
+            logStream.scrollTop = logStream.scrollHeight;
+        }
+
+        function updateFilter() {
+            const pattern = filterInput.value.trim();
+            filterInput.classList.remove('regex-error');
+            if (pattern) {
+                try {
+                    regexFilter = new RegExp(pattern);
+                } catch (e) {
+                    console.error("Invalid regex pattern:", e);
+                    regexFilter = null;
+                    filterInput.classList.add('regex-error');
+                    return
+                }
+            } else {
+                regexFilter = null;
+            }
+
+            render();
+        }
+
+        filterInput.addEventListener('input', updateFilter);
+        document.getElementById('clear-button').addEventListener('click', () => {
+            filterInput.value = "";
+            regexFilter = null;
+            render();
+        });
+        setupEventSource();
+        updateFilter();
     </script>
 </body>
 </html>

proxy/html_files.go

@@ -0,0 +1,10 @@
+package proxy
+
+import "embed"
+
+//go:embed html
+var htmlFiles embed.FS
+
+func getHTMLFile(path string) ([]byte, error) {
+	return htmlFiles.ReadFile("html/" + path)
+}

proxy/logMonitor.go

@@ -46,7 +46,7 @@ func (w *LogMonitor) Write(p []byte) (n int, err error) {
 	w.buffer = w.buffer.Next()
 	w.bufferMu.Unlock()
 
-	w.broadcast(p)
+	w.broadcast(bufferCopy)
 	return n, nil
 }
 

proxy/process.go

@@ -17,14 +17,19 @@ import (
 type ProcessState string
 
 const (
-	StateStopped ProcessState = ProcessState("stopped")
-	StateReady   ProcessState = ProcessState("ready")
-	StateFailed  ProcessState = ProcessState("failed")
+	StateStopped  ProcessState = ProcessState("stopped")
+	StateStarting ProcessState = ProcessState("starting")
+	StateReady    ProcessState = ProcessState("ready")
+	StateStopping ProcessState = ProcessState("stopping")
+
+	// failed a health check on start and will not be recovered
+	StateFailed ProcessState = ProcessState("failed")
+
+	// process is shutdown and will not be restarted
+	StateShutdown ProcessState = ProcessState("shutdown")
 )
 
 type Process struct {
-	sync.Mutex
-
 	ID                 string
 	config             ModelConfig
 	cmd                *exec.Cmd
@@ -37,9 +42,17 @@ type Process struct {
 	state      ProcessState
 
 	inFlightRequests sync.WaitGroup
+
+	// used to block on multiple start() calls
+	waitStarting sync.WaitGroup
+
+	// for managing shutdown state
+	shutdownCtx    context.Context
+	shutdownCancel context.CancelFunc
 }
 
 func NewProcess(ID string, healthCheckTimeout int, config ModelConfig, logMonitor *LogMonitor) *Process {
+	ctx, cancel := context.WithCancel(context.Background())
 	return &Process{
 		ID:                 ID,
 		config:             config,
@@ -47,22 +60,88 @@ func NewProcess(ID string, healthCheckTimeout int, config ModelConfig, logMonito
 		logMonitor:         logMonitor,
 		healthCheckTimeout: healthCheckTimeout,
 		state:              StateStopped,
+		shutdownCtx:        ctx,
+		shutdownCancel:     cancel,
 	}
 }
 
-// start the process and returns when it is ready
+func (p *Process) setState(newState ProcessState) error {
+	// enforce valid state transitions
+	invalidTransition := false
+	if p.state == StateStopped {
+		// stopped -> starting
+		if newState != StateStarting {
+			invalidTransition = true
+		}
+	} else if p.state == StateStarting {
+		// starting -> ready | failed | stopping
+		if newState != StateReady && newState != StateFailed && newState != StateStopping {
+			invalidTransition = true
+		}
+	} else if p.state == StateReady {
+		// ready -> stopping
+		if newState != StateStopping {
+			invalidTransition = true
+		}
+	} else if p.state == StateStopping {
+		// stopping -> stopped | shutdown
+		if newState != StateStopped && newState != StateShutdown {
+			invalidTransition = true
+		}
+	} else if p.state == StateFailed || p.state == StateShutdown {
+		invalidTransition = true
+	}
+
+	if invalidTransition {
+		//panic(fmt.Sprintf("Invalid state transition from %s to %s", p.state, newState))
+		return fmt.Errorf("invalid state transition from %s to %s", p.state, newState)
+	}
+
+	p.state = newState
+	return nil
+}
+
+func (p *Process) CurrentState() ProcessState {
+	p.stateMutex.RLock()
+	defer p.stateMutex.RUnlock()
+	return p.state
+}
+
+// start starts the upstream command, checks the health endpoint, and sets the state to Ready
+// it is a private method because starting is automatic but stopping can be called
+// at any time.
 func (p *Process) start() error {
 
+	if p.config.Proxy == "" {
+		return fmt.Errorf("can not start(), upstream proxy missing")
+	}
+
+	// wait for the other start() to complete
+	curState := p.CurrentState()
+
+	if curState == StateReady {
+		return nil
+	}
+
+	if curState == StateStarting {
+		p.waitStarting.Wait()
+
+		if state := p.CurrentState(); state != StateReady {
+			return fmt.Errorf("start() failed current state: %v", state)
+		}
+
+		return nil
+	}
+
 	p.stateMutex.Lock()
 	defer p.stateMutex.Unlock()
 
-	if p.state == StateReady {
-		return nil
+	if err := p.setState(StateStarting); err != nil {
+		return err
 	}
 
-	if p.state == StateFailed {
-		return fmt.Errorf("process is in a failed state and can not be restarted")
-	}
+	p.waitStarting.Add(1)
+	defer p.waitStarting.Done()
 
 	args, err := p.config.SanitizedCommand()
 	if err != nil {
@@ -77,7 +156,8 @@ func (p *Process) start() error {
 	err = p.cmd.Start()
 
 	if err != nil {
-		return err
+		p.setState(StateFailed)
+		return fmt.Errorf("start() failed: %v", err)
 	}
 
 	// One of three things can happen at this stage:
@@ -86,35 +166,56 @@ func (p *Process) start() error {
 	// 3. The health check passes
 	//
 	// only in the third case will the process be considered Ready to accept
-	healthCheckContext, cancelHealthCheck := context.WithCancelCause(context.Background())
-	defer cancelHealthCheck(nil) // clean up
-	cmdWaitChan := make(chan error, 1)
-	healthCheckChan := make(chan error, 1)
+	<-time.After(250 * time.Millisecond) // give process a bit of time to start
 
-	go func() {
-		// possible cmd exits early
-		cmdWaitChan <- p.cmd.Wait()
-	}()
+	checkStartTime := time.Now()
+	maxDuration := time.Second * time.Duration(p.healthCheckTimeout)
+	checkEndpoint := strings.TrimSpace(p.config.CheckEndpoint)
 
-	go func() {
-		<-time.After(250 * time.Millisecond) // give process a bit of time to start
-		healthCheckChan <- p.checkHealthEndpoint(healthCheckContext)
-	}()
-
-	select {
-	case err := <-cmdWaitChan:
-		p.state = StateFailed
-		if err != nil {
-			err = fmt.Errorf("command [%s] %s", strings.Join(p.cmd.Args, " "), err.Error())
-		} else {
-			err = fmt.Errorf("command [%s] exited unexpected", strings.Join(p.cmd.Args, " "))
+	// a "none" means don't check for health ... I could have picked a better word :facepalm:
+	if checkEndpoint != "none" {
+		// keep default behaviour
+		if checkEndpoint == "" {
+			checkEndpoint = "/health"
 		}
-		cancelHealthCheck(err)
-		return err
-	case err := <-healthCheckChan:
+
+		proxyTo := p.config.Proxy
+		healthURL, err := url.JoinPath(proxyTo, checkEndpoint)
 		if err != nil {
-			p.state = StateFailed
-			return err
+			return fmt.Errorf("failed to create health check URL proxy=%s and checkEndpoint=%s", proxyTo, checkEndpoint)
+		}
+
+		checkDeadline, cancelHealthCheck := context.WithDeadline(
+			context.Background(),
+			checkStartTime.Add(maxDuration),
+		)
+		defer cancelHealthCheck()
+
+		// Health check loop
+	loop:
+		for {
+			select {
+			case <-checkDeadline.Done():
+				p.setState(StateFailed)
+				return fmt.Errorf("health check failed after %vs", maxDuration.Seconds())
+			case <-p.shutdownCtx.Done():
+				return errors.New("health check interrupted due to shutdown")
+			default:
+				if err := p.checkHealthEndpoint(healthURL); err == nil {
+					cancelHealthCheck()
+					break loop
+				} else {
+					if strings.Contains(err.Error(), "connection refused") {
+						endTime, _ := checkDeadline.Deadline()
+						ttl := time.Until(endTime)
+						fmt.Fprintf(p.logMonitor, "!!! Connection refused on %s, ttl %.0fs\n", healthURL, ttl.Seconds())
+					} else {
+						fmt.Fprintf(p.logMonitor, "!!! Health check error: %v\n", err)
+					}
+				}
+			}
+
+			<-time.After(5 * time.Second)
 		}
 	}
 
@@ -125,172 +226,158 @@ func (p *Process) start() error {
 			maxDuration := time.Duration(p.config.UnloadAfter) * time.Second
 
 			for range time.Tick(time.Second) {
+				if p.state != StateReady {
+					return
+				}
+
 				// wait for all inflight requests to complete and ticker
 				p.inFlightRequests.Wait()
 
 				if time.Since(p.lastRequestHandled) > maxDuration {
-					fmt.Fprintf(p.logMonitor, "!!! Unloading model %s, TTL of %d reached.\n", p.ID, p.config.UnloadAfter)
+					fmt.Fprintf(p.logMonitor, "!!! Unloading model %s, TTL of %ds reached.\n", p.ID, p.config.UnloadAfter)
 					p.Stop()
+					return
 				}
 			}
 		}()
 	}
 
-	p.state = StateReady
-	return nil
+	return p.setState(StateReady)
 }
 
 func (p *Process) Stop() {
 	// wait for any inflight requests before proceeding
 	p.inFlightRequests.Wait()
-
 	p.stateMutex.Lock()
 	defer p.stateMutex.Unlock()
 
-	if p.state != StateReady {
+	// calling Stop() when state is invalid is a no-op
+	if err := p.setState(StateStopping); err != nil {
+		fmt.Fprintf(p.logMonitor, "!!! Info - Stop() err: %v\n", err)
 		return
 	}
 
-	if p.cmd == nil || p.cmd.Process == nil {
-		// this situation should never happen... but if it does just update the state
-		fmt.Fprintf(p.logMonitor, "!!! State is Ready but Command is nil.")
-		p.state = StateStopped
-		return
+	// stop the process with a graceful exit timeout
+	p.stopCommand(5 * time.Second)
+
+	if err := p.setState(StateStopped); err != nil {
+		panic(fmt.Sprintf("Stop() failed to set state to stopped: %v", err))
 	}
+}
 
-	// Pretty sure this stopping code needs some work for windows and
-	// will be a source of pain in the future.
+// Shutdown is called when llama-swap is shutting down. It will give a little bit
+// of time for any inflight requests to complete before shutting down. If the Process
+// is in the state of starting, it will cancel it and shut it down
+func (p *Process) Shutdown() {
+	// cancel anything that can be interrupted by a shutdown (ie: healthcheck)
+	p.shutdownCancel()
 
-	p.cmd.Process.Signal(syscall.SIGTERM)
-	ctx, cancel := context.WithTimeout(context.Background(), 5*time.Second)
-	defer cancel()
+	p.stateMutex.Lock()
+	defer p.stateMutex.Unlock()
+	p.setState(StateStopping)
 
-	done := make(chan error, 1)
+	// 5 seconds to stop the process
+	p.stopCommand(5 * time.Second)
+	if err := p.setState(StateShutdown); err != nil {
+		fmt.Printf("!!! Shutdown() failed to set state to shutdown: %v", err)
+	}
+	p.setState(StateShutdown)
+}
+
+// stopCommand will send a SIGTERM to the process and wait for it to exit.
+// If it does not exit within 5 seconds, it will send a SIGKILL.
+func (p *Process) stopCommand(sigtermTTL time.Duration) {
+	sigtermTimeout, cancelTimeout := context.WithTimeout(context.Background(), sigtermTTL)
+	defer cancelTimeout()
+
+	sigtermNormal := make(chan error, 1)
 	go func() {
-		done <- p.cmd.Wait()
+		sigtermNormal <- p.cmd.Wait()
 	}()
 
+	if p.cmd == nil || p.cmd.Process == nil {
+		fmt.Fprintf(p.logMonitor, "!!! process [%s] cmd or cmd.Process is nil", p.ID)
+		return
+	}
+
+	p.cmd.Process.Signal(syscall.SIGTERM)
+
 	select {
-	case <-ctx.Done():
-		fmt.Printf("!!! process for %s timed out waiting to stop\n", p.ID)
+	case <-sigtermTimeout.Done():
+		fmt.Fprintf(p.logMonitor, "!!! process [%s] timed out waiting to stop, sending KILL signal\n", p.ID)
 		p.cmd.Process.Kill()
-		p.cmd.Wait()
-	case err := <-done:
+	case err := <-sigtermNormal:
 		if err != nil {
-			if err.Error() != "wait: no child processes" {
-				// possible that simple-responder for testing is just not
-				// existing right, so suppress those errors.
-				fmt.Printf("!!! process for %s stopped with error > %v\n", p.ID, err)
-			}
-		}
-	}
-	p.state = StateStopped
-}
-
-func (p *Process) CurrentState() ProcessState {
-	p.stateMutex.RLock()
-	defer p.stateMutex.RUnlock()
-	return p.state
-}
-
-func (p *Process) checkHealthEndpoint(ctxFromStart context.Context) error {
-	if p.config.Proxy == "" {
-		return fmt.Errorf("no upstream available to check /health")
-	}
-
-	checkEndpoint := strings.TrimSpace(p.config.CheckEndpoint)
-
-	if checkEndpoint == "none" {
-		return nil
-	}
-
-	// keep default behaviour
-	if checkEndpoint == "" {
-		checkEndpoint = "/health"
-	}
-
-	proxyTo := p.config.Proxy
-	maxDuration := time.Second * time.Duration(p.healthCheckTimeout)
-	healthURL, err := url.JoinPath(proxyTo, checkEndpoint)
-	if err != nil {
-		return fmt.Errorf("failed to create health url with with %s and path %s", proxyTo, checkEndpoint)
-	}
-
-	client := &http.Client{}
-	startTime := time.Now()
-
-	for {
-		req, err := http.NewRequest("GET", healthURL, nil)
-		if err != nil {
-			return err
-		}
-
-		ctx, cancel := context.WithTimeout(ctxFromStart, time.Second)
-		defer cancel()
-		req = req.WithContext(ctx)
-		resp, err := client.Do(req)
-
-		ttl := (maxDuration - time.Since(startTime)).Seconds()
-
-		if err != nil {
-			// check if the context was cancelled
-			select {
-			case <-ctx.Done():
-				err := context.Cause(ctx)
-				if !errors.Is(err, context.DeadlineExceeded) {
-					return err
+			if errno, ok := err.(syscall.Errno); ok {
+				fmt.Fprintf(p.logMonitor, "!!! process [%s] errno >> %v\n", p.ID, errno)
+			} else if exitError, ok := err.(*exec.ExitError); ok {
+				if strings.Contains(exitError.String(), "signal: terminated") {
+					fmt.Fprintf(p.logMonitor, "!!! process [%s] stopped OK\n", p.ID)
+				} else if strings.Contains(exitError.String(), "signal: interrupt") {
+					fmt.Fprintf(p.logMonitor, "!!! process [%s] interrupted OK\n", p.ID)
+				} else {
+					fmt.Fprintf(p.logMonitor, "!!! process [%s] ExitError >> %v, exit code: %d\n", p.ID, exitError, exitError.ExitCode())
 				}
-			default:
-			}
 
-			// wait a bit longer for TCP connection issues
-			if strings.Contains(err.Error(), "connection refused") {
-				fmt.Fprintf(p.logMonitor, "Connection refused on %s, ttl %.0fs\n", healthURL, ttl)
-				time.Sleep(5 * time.Second)
 			} else {
-				time.Sleep(time.Second)
+				fmt.Fprintf(p.logMonitor, "!!! process [%s] exited >> %v\n", p.ID, err)
 			}
-
-			if ttl < 0 {
-				return fmt.Errorf("failed to check health from: %s", healthURL)
-			}
-
-			continue
 		}
-
-		defer resp.Body.Close()
-		if resp.StatusCode == http.StatusOK {
-			return nil
-		}
-
-		if ttl < 0 {
-			return fmt.Errorf("failed to check health from: %s", healthURL)
-		}
-
-		time.Sleep(time.Second)
 	}
 }
 
+func (p *Process) checkHealthEndpoint(healthURL string) error {
+
+	client := &http.Client{
+		Timeout: 500 * time.Millisecond,
+	}
+
+	req, err := http.NewRequest("GET", healthURL, nil)
+	if err != nil {
+		return err
+	}
+
+	resp, err := client.Do(req)
+	if err != nil {
+		return err
+	}
+	defer resp.Body.Close()
+
+	// got a response but it was not an OK
+	if resp.StatusCode != http.StatusOK {
+		return fmt.Errorf("status code: %d", resp.StatusCode)
+	}
+
+	return nil
+}
+
 func (p *Process) ProxyRequest(w http.ResponseWriter, r *http.Request) {
 
-	p.inFlightRequests.Add(1)
+	// prevent new requests from being made while stopping or irrecoverable
+	currentState := p.CurrentState()
+	if currentState == StateFailed || currentState == StateShutdown || currentState == StateStopping {
+		http.Error(w, fmt.Sprintf("Process can not ProxyRequest, state is %s", currentState), http.StatusServiceUnavailable)
+		return
+	}
 
+	p.inFlightRequests.Add(1)
 	defer func() {
 		p.lastRequestHandled = time.Now()
 		p.inFlightRequests.Done()
 	}()
 
+	// start the process on demand
 	if p.CurrentState() != StateReady {
 		if err := p.start(); err != nil {
 			errstr := fmt.Sprintf("unable to start process: %s", err)
-			http.Error(w, errstr, http.StatusInternalServerError)
+			http.Error(w, errstr, http.StatusBadGateway)
 			return
 		}
 	}
 
 	proxyTo := p.config.Proxy
 	client := &http.Client{}
-	req, err := http.NewRequest(r.Method, proxyTo+r.URL.String(), r.Body)
+	req, err := http.NewRequestWithContext(r.Context(), r.Method, proxyTo+r.URL.String(), r.Body)
 	if err != nil {
 		http.Error(w, err.Error(), http.StatusInternalServerError)
 		return

proxy/process_test.go

@@ -48,6 +48,33 @@ func TestProcess_AutomaticallyStartsUpstream(t *testing.T) {
 	}
 }
 
+// TestProcess_WaitOnMultipleStarts tests that multiple concurrent requests
+// are all handled successfully, even though they all may ask for the process to .start()
+func TestProcess_WaitOnMultipleStarts(t *testing.T) {
+
+	logMonitor := NewLogMonitorWriter(io.Discard)
+	expectedMessage := "testing91931"
+	config := getTestSimpleResponderConfig(expectedMessage)
+
+	process := NewProcess("test-process", 5, config, logMonitor)
+	defer process.Stop()
+
+	var wg sync.WaitGroup
+	for i := 0; i < 5; i++ {
+		wg.Add(1)
+		go func(reqID int) {
+			defer wg.Done()
+			req := httptest.NewRequest("GET", "/test", nil)
+			w := httptest.NewRecorder()
+			process.ProxyRequest(w, req)
+			assert.Equal(t, http.StatusOK, w.Code, "Worker %d got wrong HTTP code", reqID)
+			assert.Contains(t, w.Body.String(), expectedMessage, "Worker %d got wrong message", reqID)
+		}(i)
+	}
+	wg.Wait()
+	assert.Equal(t, StateReady, process.CurrentState())
+}
+
 // test that the automatic start returns the expected error type
 func TestProcess_BrokenModelConfig(t *testing.T) {
 	// Create a process configuration
@@ -58,16 +85,19 @@ func TestProcess_BrokenModelConfig(t *testing.T) {
 	}
 
 	process := NewProcess("broken", 1, config, NewLogMonitor())
-	defer process.Stop()
 
 	req := httptest.NewRequest("GET", "/", nil)
 	w := httptest.NewRecorder()
 	process.ProxyRequest(w, req)
-	assert.Equal(t, http.StatusInternalServerError, w.Code)
+	assert.Equal(t, http.StatusBadGateway, w.Code)
 	assert.Contains(t, w.Body.String(), "unable to start process")
+
+	w = httptest.NewRecorder()
+	process.ProxyRequest(w, req)
+	assert.Equal(t, http.StatusServiceUnavailable, w.Code)
+	assert.Contains(t, w.Body.String(), "Process can not ProxyRequest, state is failed")
 }
 
-// test that the process unloads after the TTL
 func TestProcess_UnloadAfterTTL(t *testing.T) {
 	if testing.Short() {
 		t.Skip("skipping long auto unload TTL test")
@@ -79,7 +109,7 @@ func TestProcess_UnloadAfterTTL(t *testing.T) {
 	config.UnloadAfter = 3 // seconds
 	assert.Equal(t, 3, config.UnloadAfter)
 
-	process := NewProcess("ttl", 2, config, NewLogMonitorWriter(io.Discard))
+	process := NewProcess("ttl_test", 2, config, NewLogMonitorWriter(io.Discard))
 	defer process.Stop()
 
 	// this should take 4 seconds
@@ -111,6 +141,33 @@ func TestProcess_UnloadAfterTTL(t *testing.T) {
 	assert.Equal(t, StateStopped, process.CurrentState())
 }
 
+func TestProcess_LowTTLValue(t *testing.T) {
+	if true { // change this code to run this ...
+		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)
+
+	process := NewProcess("ttl", 2, config, NewLogMonitorWriter(os.Stdout))
+	defer process.Stop()
+
+	for i := 0; i < 100; i++ {
+		t.Logf("Waiting before sending request %d", i)
+		time.Sleep(1500 * time.Millisecond)
+
+		expected := fmt.Sprintf("echo=test_%d", i)
+		req := httptest.NewRequest("GET", fmt.Sprintf("/slow-respond?echo=%s&delay=50ms", expected), nil)
+		w := httptest.NewRecorder()
+		process.ProxyRequest(w, req)
+		assert.Equal(t, http.StatusOK, w.Code)
+		assert.Contains(t, w.Body.String(), expected)
+	}
+
+}
+
 // issue #19
 func TestProcess_HTTPRequestsHaveTimeToFinish(t *testing.T) {
 	if testing.Short() {
@@ -164,3 +221,85 @@ func TestProcess_HTTPRequestsHaveTimeToFinish(t *testing.T) {
 		assert.Equal(t, key, result)
 	}
 }
+
+func TestSetState(t *testing.T) {
+	tests := []struct {
+		name           string
+		currentState   ProcessState
+		newState       ProcessState
+		expectedError  error
+		expectedResult ProcessState
+	}{
+		{"Stopped to Starting", StateStopped, StateStarting, nil, StateStarting},
+		{"Starting to Ready", StateStarting, StateReady, nil, StateReady},
+		{"Starting to Failed", StateStarting, StateFailed, nil, StateFailed},
+		{"Starting to Stopping", StateStarting, StateStopping, nil, StateStopping},
+		{"Ready to Stopping", StateReady, StateStopping, nil, StateStopping},
+		{"Stopping to Stopped", StateStopping, StateStopped, nil, StateStopped},
+		{"Stopping to Shutdown", StateStopping, StateShutdown, nil, StateShutdown},
+		{"Stopped to Ready", StateStopped, StateReady, fmt.Errorf("invalid state transition from stopped to ready"), StateStopped},
+		{"Starting to Stopped", StateStarting, StateStopped, fmt.Errorf("invalid state transition from starting to stopped"), StateStarting},
+		{"Ready to Starting", StateReady, StateStarting, fmt.Errorf("invalid state transition from ready to starting"), StateReady},
+		{"Ready to Failed", StateReady, StateFailed, fmt.Errorf("invalid state transition from ready to failed"), StateReady},
+		{"Stopping to Ready", StateStopping, StateReady, fmt.Errorf("invalid state transition from stopping to ready"), StateStopping},
+		{"Failed to Stopped", StateFailed, StateStopped, fmt.Errorf("invalid state transition from failed to stopped"), StateFailed},
+		{"Failed to Starting", StateFailed, StateStarting, fmt.Errorf("invalid state transition from failed to starting"), StateFailed},
+		{"Shutdown to Stopped", StateShutdown, StateStopped, fmt.Errorf("invalid state transition from shutdown to stopped"), StateShutdown},
+		{"Shutdown to Starting", StateShutdown, StateStarting, fmt.Errorf("invalid state transition from shutdown to starting"), StateShutdown},
+	}
+
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			p := &Process{
+				state: test.currentState,
+			}
+
+			err := p.setState(test.newState)
+			if err != nil && test.expectedError == nil {
+				t.Errorf("Unexpected error: %v", err)
+			} else if err == nil && test.expectedError != nil {
+				t.Errorf("Expected error: %v, but got none", test.expectedError)
+			} else if err != nil && test.expectedError != nil {
+				if err.Error() != test.expectedError.Error() {
+					t.Errorf("Expected error: %v, got: %v", test.expectedError, err)
+				}
+			}
+
+			if p.state != test.expectedResult {
+				t.Errorf("Expected state: %v, got: %v", test.expectedResult, p.state)
+			}
+		})
+	}
+}
+
+func TestProcess_ShutdownInterruptsHealthCheck(t *testing.T) {
+	if testing.Short() {
+		t.Skip("skipping long shutdown test")
+	}
+
+	logMonitor := NewLogMonitorWriter(io.Discard)
+	expectedMessage := "testing91931"
+
+	// make a config where the healthcheck will always fail because port is wrong
+	config := getTestSimpleResponderConfigPort(expectedMessage, 9999)
+	config.Proxy = "http://localhost:9998/test"
+
+	healthCheckTTLSeconds := 30
+	process := NewProcess("test-process", healthCheckTTLSeconds, config, logMonitor)
+
+	// start a goroutine to simulate a shutdown
+	var wg sync.WaitGroup
+	go func() {
+		defer wg.Done()
+		<-time.After(time.Second * 2)
+		process.Shutdown()
+	}()
+	wg.Add(1)
+
+	// start the process, this is a blocking call
+	err := process.start()
+
+	wg.Wait()
+	assert.ErrorContains(t, err, "health check interrupted due to shutdown")
+	assert.Equal(t, StateShutdown, process.CurrentState())
+}

proxy/proxymanager.go

@@ -6,12 +6,15 @@ import (
 	"fmt"
 	"io"
 	"net/http"
+	"sort"
 	"strconv"
 	"strings"
 	"sync"
 	"time"
 
 	"github.com/gin-gonic/gin"
+	"github.com/tidwall/gjson"
+	"github.com/tidwall/sjson"
 )
 
 const (
@@ -35,11 +38,63 @@ func New(config *Config) *ProxyManager {
 		ginEngine:        gin.New(),
 	}
 
-	// Set up routes using the Gin engine
-	pm.ginEngine.POST("/v1/chat/completions", pm.proxyChatRequestHandler)
+	if config.LogRequests {
+		pm.ginEngine.Use(func(c *gin.Context) {
+			// Start timer
+			start := time.Now()
 
+			// capture these because /upstream/:model rewrites them in c.Next()
+			clientIP := c.ClientIP()
+			method := c.Request.Method
+			path := c.Request.URL.Path
+
+			// Process request
+			c.Next()
+
+			// Stop timer
+			duration := time.Since(start)
+
+			statusCode := c.Writer.Status()
+			bodySize := c.Writer.Size()
+
+			fmt.Fprintf(pm.logMonitor, "[llama-swap] %s [%s] \"%s %s %s\" %d %d \"%s\" %v\n",
+				clientIP,
+				time.Now().Format("2006-01-02 15:04:05"),
+				method,
+				path,
+				c.Request.Proto,
+				statusCode,
+				bodySize,
+				c.Request.UserAgent(),
+				duration,
+			)
+		})
+	}
+
+	// see: https://github.com/mostlygeek/llama-swap/issues/42
+	// respond with permissive OPTIONS for any endpoint
+	pm.ginEngine.Use(func(c *gin.Context) {
+		if c.Request.Method == "OPTIONS" {
+			c.Header("Access-Control-Allow-Origin", "*")
+			c.Header("Access-Control-Allow-Methods", "GET, POST, OPTIONS")
+			c.Header("Access-Control-Allow-Headers", "Content-Type, Authorization")
+			c.AbortWithStatus(204)
+			return
+		}
+		c.Next()
+	})
+
+	// Set up routes using the Gin engine
+	pm.ginEngine.POST("/v1/chat/completions", pm.proxyOAIHandler)
 	// Support legacy /v1/completions api, see issue #12
-	pm.ginEngine.POST("/v1/completions", pm.proxyChatRequestHandler)
+	pm.ginEngine.POST("/v1/completions", pm.proxyOAIHandler)
+
+	// Support embeddings
+	pm.ginEngine.POST("/v1/embeddings", pm.proxyOAIHandler)
+	pm.ginEngine.POST("/v1/rerank", pm.proxyOAIHandler)
+
+	// Support audio/speech endpoint
+	pm.ginEngine.POST("/v1/audio/speech", pm.proxyOAIHandler)
 
 	pm.ginEngine.GET("/v1/models", pm.listModelsHandler)
 
@@ -48,7 +103,35 @@ func New(config *Config) *ProxyManager {
 	pm.ginEngine.GET("/logs/stream", pm.streamLogsHandler)
 	pm.ginEngine.GET("/logs/streamSSE", pm.streamLogsHandlerSSE)
 
-	pm.ginEngine.NoRoute(pm.proxyNoRouteHandler)
+	pm.ginEngine.GET("/upstream", pm.upstreamIndex)
+	pm.ginEngine.Any("/upstream/:model_id/*upstreamPath", pm.proxyToUpstream)
+
+	pm.ginEngine.GET("/unload", pm.unloadAllModelsHandler)
+
+	pm.ginEngine.GET("/", func(c *gin.Context) {
+		// Set the Content-Type header to text/html
+		c.Header("Content-Type", "text/html")
+
+		// Write the embedded HTML content to the response
+		htmlData, err := getHTMLFile("index.html")
+		if err != nil {
+			c.String(http.StatusInternalServerError, err.Error())
+			return
+		}
+		_, err = c.Writer.Write(htmlData)
+		if err != nil {
+			c.String(http.StatusInternalServerError, fmt.Sprintf("failed to write response: %v", err))
+			return
+		}
+	})
+
+	pm.ginEngine.GET("/favicon.ico", func(c *gin.Context) {
+		if data, err := getHTMLFile("favicon.ico"); err == nil {
+			c.Data(http.StatusOK, "image/x-icon", data)
+		} else {
+			c.String(http.StatusInternalServerError, err.Error())
+		}
+	})
 
 	// Disable console color for testing
 	gin.DisableConsoleColor()
@@ -77,16 +160,45 @@ func (pm *ProxyManager) stopProcesses() {
 		return
 	}
 
+	// stop Processes in parallel
+	var wg sync.WaitGroup
 	for _, process := range pm.currentProcesses {
-		process.Stop()
+		wg.Add(1)
+		go func(process *Process) {
+			defer wg.Done()
+			process.Stop()
+		}(process)
 	}
+	wg.Wait()
 
 	pm.currentProcesses = make(map[string]*Process)
 }
 
+// Shutdown is called to shutdown all upstream processes
+// when llama-swap is shutting down.
+func (pm *ProxyManager) Shutdown() {
+	pm.Lock()
+	defer pm.Unlock()
+
+	// shutdown process in parallel
+	var wg sync.WaitGroup
+	for _, process := range pm.currentProcesses {
+		wg.Add(1)
+		go func(process *Process) {
+			defer wg.Done()
+			process.Shutdown()
+		}(process)
+	}
+	wg.Wait()
+}
+
 func (pm *ProxyManager) listModelsHandler(c *gin.Context) {
 	data := []interface{}{}
-	for id := range pm.config.Models {
+	for id, modelConfig := range pm.config.Models {
+		if modelConfig.Unlisted {
+			continue
+		}
+
 		data = append(data, map[string]interface{}{
 			"id":       id,
 			"object":   "model",
@@ -104,7 +216,7 @@ func (pm *ProxyManager) listModelsHandler(c *gin.Context) {
 
 	// Encode the data as JSON and write it to the response writer
 	if err := json.NewEncoder(c.Writer).Encode(map[string]interface{}{"data": data}); err != nil {
-		c.AbortWithError(http.StatusInternalServerError, fmt.Errorf("error encoding JSON"))
+		pm.sendErrorResponse(c, http.StatusInternalServerError, fmt.Sprintf("error encoding JSON %s", err.Error()))
 		return
 	}
 }
@@ -113,12 +225,8 @@ func (pm *ProxyManager) swapModel(requestedModel string) (*Process, error) {
 	pm.Lock()
 	defer pm.Unlock()
 
-	// Check if requestedModel contains a /
-	profileName, modelName := "", requestedModel
-	if idx := strings.Index(requestedModel, PROFILE_SPLIT_CHAR); idx != -1 {
-		profileName = requestedModel[:idx]
-		modelName = requestedModel[idx+1:]
-	}
+	// Check if requestedModel contains a PROFILE_SPLIT_CHAR
+	profileName, modelName := splitRequestedModel(requestedModel)
 
 	if profileName != "" {
 		if _, found := pm.config.Profiles[profileName]; !found {
@@ -132,6 +240,21 @@ func (pm *ProxyManager) swapModel(requestedModel string) (*Process, error) {
 		return nil, fmt.Errorf("could not find modelID for %s", requestedModel)
 	}
 
+	// check if model is part of the profile
+	if profileName != "" {
+		found := false
+		for _, item := range pm.config.Profiles[profileName] {
+			if item == realModelName {
+				found = true
+				break
+			}
+		}
+
+		if !found {
+			return nil, fmt.Errorf("model %s part of profile %s", realModelName, profileName)
+		}
+	}
+
 	// exit early when already running, otherwise stop everything and swap
 	requestedProcessKey := ProcessKeyName(profileName, realModelName)
 
@@ -170,27 +293,75 @@ func (pm *ProxyManager) swapModel(requestedModel string) (*Process, error) {
 	return pm.currentProcesses[requestedProcessKey], nil
 }
 
-func (pm *ProxyManager) proxyChatRequestHandler(c *gin.Context) {
-	bodyBytes, err := io.ReadAll(c.Request.Body)
-	if err != nil {
-		c.AbortWithError(http.StatusBadRequest, fmt.Errorf("invalid JSON"))
-		return
-	}
-	var requestBody map[string]interface{}
-	if err := json.Unmarshal(bodyBytes, &requestBody); err != nil {
-		c.AbortWithError(http.StatusBadRequest, fmt.Errorf("invalid JSON"))
-		return
-	}
-	model, ok := requestBody["model"].(string)
-	if !ok {
-		c.AbortWithError(http.StatusBadRequest, fmt.Errorf("missing or invalid 'model' key"))
+func (pm *ProxyManager) proxyToUpstream(c *gin.Context) {
+	requestedModel := c.Param("model_id")
+
+	if requestedModel == "" {
+		pm.sendErrorResponse(c, http.StatusBadRequest, "model id required in path")
 		return
 	}
 
-	if process, err := pm.swapModel(model); err != nil {
-		c.AbortWithError(http.StatusNotFound, fmt.Errorf("unable to swap to model, %s", err.Error()))
+	if process, err := pm.swapModel(requestedModel); err != nil {
+		pm.sendErrorResponse(c, http.StatusNotFound, fmt.Sprintf("unable to swap to model, %s", err.Error()))
+	} else {
+		// rewrite the path
+		c.Request.URL.Path = c.Param("upstreamPath")
+		process.ProxyRequest(c.Writer, c.Request)
+	}
+}
+
+func (pm *ProxyManager) upstreamIndex(c *gin.Context) {
+	var html strings.Builder
+
+	html.WriteString("<!doctype HTML>\n<html><body><h1>Available Models</h1><ul>")
+
+	// Extract keys and sort them
+	var modelIDs []string
+	for modelID, modelConfig := range pm.config.Models {
+		if modelConfig.Unlisted {
+			continue
+		}
+
+		modelIDs = append(modelIDs, modelID)
+	}
+	sort.Strings(modelIDs)
+
+	// Iterate over sorted keys
+	for _, modelID := range modelIDs {
+		html.WriteString(fmt.Sprintf("<li><a href=\"/upstream/%s\">%s</a></li>", modelID, modelID))
+	}
+	html.WriteString("</ul></body></html>")
+	c.Header("Content-Type", "text/html")
+	c.String(http.StatusOK, html.String())
+}
+
+func (pm *ProxyManager) proxyOAIHandler(c *gin.Context) {
+	bodyBytes, err := io.ReadAll(c.Request.Body)
+	if err != nil {
+		pm.sendErrorResponse(c, http.StatusBadRequest, "could not ready request body")
+		return
+	}
+
+	requestedModel := gjson.GetBytes(bodyBytes, "model").String()
+	if requestedModel == "" {
+		pm.sendErrorResponse(c, http.StatusBadRequest, "missing or invalid 'model' key")
+	}
+
+	if process, err := pm.swapModel(requestedModel); err != nil {
+		pm.sendErrorResponse(c, http.StatusNotFound, fmt.Sprintf("unable to swap to model, %s", err.Error()))
 		return
 	} else {
+
+		// strip
+		profileName, modelName := splitRequestedModel(requestedModel)
+		if profileName != "" {
+			bodyBytes, err = sjson.SetBytes(bodyBytes, "model", modelName)
+			if err != nil {
+				pm.sendErrorResponse(c, http.StatusInternalServerError, fmt.Sprintf("error updating JSON: %s", err.Error()))
+				return
+			}
+		}
+
 		c.Request.Body = io.NopCloser(bytes.NewBuffer(bodyBytes))
 
 		// dechunk it as we already have all the body bytes see issue #11
@@ -201,16 +372,30 @@ func (pm *ProxyManager) proxyChatRequestHandler(c *gin.Context) {
 	}
 }
 
-func (pm *ProxyManager) proxyNoRouteHandler(c *gin.Context) {
-	// since maps are unordered, just use the first available process if one exists
-	for _, process := range pm.currentProcesses {
-		process.ProxyRequest(c.Writer, c.Request)
-		return
-	}
+func (pm *ProxyManager) sendErrorResponse(c *gin.Context, statusCode int, message string) {
+	acceptHeader := c.GetHeader("Accept")
 
-	c.AbortWithError(http.StatusBadRequest, fmt.Errorf("no strategy to handle request"))
+	if strings.Contains(acceptHeader, "application/json") {
+		c.JSON(statusCode, gin.H{"error": message})
+	} else {
+		c.String(statusCode, message)
+	}
+}
+
+func (pm *ProxyManager) unloadAllModelsHandler(c *gin.Context) {
+	pm.StopProcesses()
+	c.String(http.StatusOK, "OK")
 }
 
 func ProcessKeyName(groupName, modelName string) string {
 	return groupName + PROFILE_SPLIT_CHAR + modelName
 }
+
+func splitRequestedModel(requestedModel string) (string, string) {
+	profileName, modelName := "", requestedModel
+	if idx := strings.Index(requestedModel, PROFILE_SPLIT_CHAR); idx != -1 {
+		profileName = requestedModel[:idx]
+		modelName = requestedModel[idx+1:]
+	}
+	return profileName, modelName
+}

proxy/proxymanager_loghandlers.go

@@ -1,7 +1,6 @@
 package proxy
 
 import (
-	"embed"
 	"fmt"
 	"net/http"
 	"strings"
@@ -9,12 +8,6 @@ import (
 	"github.com/gin-gonic/gin"
 )
 
-//go:embed html/logs.html
-var logsHTML []byte
-
-// make sure embed is kept there by the IDE auto-package importer
-var _ = embed.FS{}
-
 func (pm *ProxyManager) sendLogsHandlers(c *gin.Context) {
 
 	accept := c.GetHeader("Accept")
@@ -23,9 +16,14 @@ func (pm *ProxyManager) sendLogsHandlers(c *gin.Context) {
 		c.Header("Content-Type", "text/html")
 
 		// Write the embedded HTML content to the response
-		_, err := c.Writer.Write(logsHTML)
+		logsHTML, err := getHTMLFile("logs.html")
 		if err != nil {
-			c.AbortWithError(http.StatusInternalServerError, fmt.Errorf("failed to write response: %v", err))
+			c.String(http.StatusInternalServerError, err.Error())
+			return
+		}
+		_, err = c.Writer.Write(logsHTML)
+		if err != nil {
+			c.String(http.StatusInternalServerError, fmt.Sprintf("failed to write response: %v", err))
 			return
 		}
 	} else {
@@ -50,7 +48,7 @@ func (pm *ProxyManager) streamLogsHandler(c *gin.Context) {
 	notify := c.Request.Context().Done()
 	flusher, ok := c.Writer.(http.Flusher)
 	if !ok {
-		c.AbortWithError(http.StatusInternalServerError, fmt.Errorf("Streaming unsupported"))
+		c.AbortWithError(http.StatusInternalServerError, fmt.Errorf("streaming unsupported"))
 		return
 	}
 
@@ -60,11 +58,7 @@ func (pm *ProxyManager) streamLogsHandler(c *gin.Context) {
 	if !skipHistory {
 		history := pm.logMonitor.GetHistory()
 		if len(history) != 0 {
-			_, err := c.Writer.Write(history)
-			if err != nil {
-				c.AbortWithError(http.StatusInternalServerError, err)
-				return
-			}
+			c.Writer.Write(history)
 			flusher.Flush()
 		}
 	}
@@ -75,7 +69,7 @@ func (pm *ProxyManager) streamLogsHandler(c *gin.Context) {
 		case msg := <-ch:
 			_, err := c.Writer.Write(msg)
 			if err != nil {
-				c.AbortWithError(http.StatusInternalServerError, err)
+				// just break the loop if we can't write for some reason
 				return
 			}
 			flusher.Flush()

proxy/proxymanager_test.go

@@ -210,3 +210,142 @@ func TestProxyManager_ListModelsHandler(t *testing.T) {
 	// Ensure all expected models were returned
 	assert.Empty(t, expectedModels, "not all expected models were returned")
 }
+
+func TestProxyManager_ProfileNonMember(t *testing.T) {
+
+	model1 := "path1/model1"
+	model2 := "path2/model2"
+
+	profileMemberName := ProcessKeyName("test", model1)
+	profileNonMemberName := ProcessKeyName("test", model2)
+
+	config := &Config{
+		HealthCheckTimeout: 15,
+		Models: map[string]ModelConfig{
+			model1: getTestSimpleResponderConfig("model1"),
+			model2: getTestSimpleResponderConfig("model2"),
+		},
+		Profiles: map[string][]string{
+			"test": {model1},
+		},
+	}
+
+	proxy := New(config)
+	defer proxy.StopProcesses()
+
+	// actual member of profile
+	{
+		reqBody := fmt.Sprintf(`{"model":"%s"}`, profileMemberName)
+		req := httptest.NewRequest("POST", "/v1/chat/completions", bytes.NewBufferString(reqBody))
+		w := httptest.NewRecorder()
+
+		proxy.HandlerFunc(w, req)
+		assert.Equal(t, http.StatusOK, w.Code)
+		assert.Contains(t, w.Body.String(), "model1")
+	}
+
+	// actual model, but non-member will 404
+	{
+		reqBody := fmt.Sprintf(`{"model":"%s"}`, profileNonMemberName)
+		req := httptest.NewRequest("POST", "/v1/chat/completions", bytes.NewBufferString(reqBody))
+		w := httptest.NewRecorder()
+
+		proxy.HandlerFunc(w, req)
+		assert.Equal(t, http.StatusNotFound, w.Code)
+	}
+}
+
+func TestProxyManager_Shutdown(t *testing.T) {
+	// make broken model configurations
+	model1Config := getTestSimpleResponderConfigPort("model1", 9991)
+	model1Config.Proxy = "http://localhost:10001/"
+
+	model2Config := getTestSimpleResponderConfigPort("model2", 9992)
+	model2Config.Proxy = "http://localhost:10002/"
+
+	model3Config := getTestSimpleResponderConfigPort("model3", 9993)
+	model3Config.Proxy = "http://localhost:10003/"
+
+	config := &Config{
+		HealthCheckTimeout: 15,
+		Profiles: map[string][]string{
+			"test": {"model1", "model2", "model3"},
+		},
+		Models: map[string]ModelConfig{
+			"model1": model1Config,
+			"model2": model2Config,
+			"model3": model3Config,
+		},
+	}
+
+	proxy := New(config)
+
+	// Start all the processes
+	var wg sync.WaitGroup
+	for _, modelName := range []string{"test:model1", "test:model2", "test:model3"} {
+		wg.Add(1)
+		go func(modelName string) {
+			defer wg.Done()
+			reqBody := fmt.Sprintf(`{"model":"%s"}`, modelName)
+			req := httptest.NewRequest("POST", "/v1/chat/completions", bytes.NewBufferString(reqBody))
+			w := httptest.NewRecorder()
+
+			// send a request to trigger the proxy to load
+			proxy.HandlerFunc(w, req)
+			assert.Equal(t, http.StatusBadGateway, w.Code)
+			assert.Contains(t, w.Body.String(), "health check interrupted due to shutdown")
+			//fmt.Println(w.Code, w.Body.String())
+		}(modelName)
+	}
+
+	go func() {
+		<-time.After(time.Second)
+		proxy.Shutdown()
+	}()
+	wg.Wait()
+}
+
+func TestProxyManager_Unload(t *testing.T) {
+	config := &Config{
+		HealthCheckTimeout: 15,
+		Models: map[string]ModelConfig{
+			"model1": getTestSimpleResponderConfig("model1"),
+		},
+	}
+
+	proxy := New(config)
+	proc, err := proxy.swapModel("model1")
+	assert.NoError(t, err)
+	assert.NotNil(t, proc)
+
+	assert.Len(t, proxy.currentProcesses, 1)
+	req := httptest.NewRequest("GET", "/unload", nil)
+	w := httptest.NewRecorder()
+	proxy.HandlerFunc(w, req)
+	assert.Equal(t, http.StatusOK, w.Code)
+	assert.Equal(t, w.Body.String(), "OK")
+	assert.Len(t, proxy.currentProcesses, 0)
+}
+
+// issue 62, strip profile slug from model name
+func TestProxyManager_StripProfileSlug(t *testing.T) {
+	config := &Config{
+		HealthCheckTimeout: 15,
+		Profiles: map[string][]string{
+			"test": {"TheExpectedModel"}, // TheExpectedModel is default in simple-responder.go
+		},
+		Models: map[string]ModelConfig{
+			"TheExpectedModel": getTestSimpleResponderConfig("TheExpectedModel"),
+		},
+	}
+
+	proxy := New(config)
+	defer proxy.StopProcesses()
+
+	reqBody := fmt.Sprintf(`{"model":"%s"}`, "test:TheExpectedModel")
+	req := httptest.NewRequest("POST", "/v1/audio/speech", bytes.NewBufferString(reqBody))
+	w := httptest.NewRecorder()
+	proxy.HandlerFunc(w, req)
+	assert.Equal(t, http.StatusOK, w.Code)
+	assert.Contains(t, w.Body.String(), "ok")
+}