increase health check to a minimum of 5 seconds

.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
 

.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

@@ -35,6 +35,11 @@ linux:
 	@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
 
+# 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:
 	@echo "Building simple responder"
@@ -60,4 +65,4 @@ release:
 	git tag "$$new_tag";
 
 # Phony targets
-.PHONY: all clean osx linux
+.PHONY: all clean mac linux windows simple-responder

README.md

@@ -1,21 +1,10 @@
-# llama-swap
-
 ![llama-swap header image](header.jpeg)
 
-# Introduction
+# llama-swap
+
 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).
-
-Download a pre-built [release](https://github.com/mostlygeek/llama-swap/releases) or build it yourself from source with `make clean all`.
-
-## How does it work?
-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 a server is already running it will stop it and start 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.
-
-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.
-
-## 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. This provides clean environment isolation as well as responding correctly to `SIGTERM` signals to shutdown.
+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:
 
@@ -31,16 +20,42 @@ Any OpenAI compatible server would work. llama-swap was originally designed for
   - `v1/audio/speech` ([#36](https://github.com/mostlygeek/llama-swap/issues/36))
 - ✅ Multiple GPU support
 - ✅ Docker and Podman support
-- ✅ Run multiple models at once with `profiles`
+- ✅ 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
 - ✅ Use any local OpenAI compatible server (llama.cpp, vllm, tabbyAPI, etc)
 - ✅ Direct access to upstream HTTP server via `/upstream/:model_id` ([demo](https://github.com/mostlygeek/llama-swap/pull/31))
 
+## How does llama-swap work?
+
+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.
+
+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
@@ -59,8 +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
@@ -87,8 +102,8 @@ models:
   # unlisted models do not show up in /v1/models or /upstream lists
   # but they can still be requested as normal
   "qwen-unlisted":
-    cmd: llama-server --port 9999 -m Llama-3.2-1B-Instruct-Q4_K_M.gguf -ngl 0
     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":
@@ -117,11 +132,63 @@ profiles:
 - [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.
 
-### Installation
+</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
@@ -151,11 +218,18 @@ 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

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" ]

proxy/process.go

@@ -215,7 +215,7 @@ func (p *Process) start() error {
 				}
 			}
 
-			<-time.After(time.Second)
+			<-time.After(5 * time.Second)
 		}
 	}
 
@@ -296,7 +296,8 @@ func (p *Process) stopCommand(sigtermTTL time.Duration) {
 	}()
 
 	if p.cmd == nil || p.cmd.Process == nil {
-		panic("this should not happen, cmd or cmd.Process is nil")
+		fmt.Fprintf(p.logMonitor, "!!! process [%s] cmd or cmd.Process is nil", p.ID)
+		return
 	}
 
 	p.cmd.Process.Signal(syscall.SIGTERM)