remove panic() when cmd or process is nil

Introduce `Process.Shutdown()` and `ProxyManager.Shutdown()`. These two function required a lot of internal process state management refactoring. A key benefit is that `Process.start()` is now interruptable. When `Shutdown()` is called it will break the long health check loop. 

State management within Process is also improved. Added `starting`, `stopping` and `shutdown` states. Additionally, introduced a simple finite state machine to manage transitions.

.github/workflows/release.yml

@@ -30,4 +30,4 @@ 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

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 +28,12 @@ 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
 
 # for testing proxy.Process
 simple-responder:
@@ -35,5 +45,19 @@ 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

README.md

@@ -2,19 +2,40 @@
 
 ![llama-swap header image](header.jpeg)
 
-llama-swap is a golang server that automatically swaps the llama.cpp server on demand. 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!
+# Introduction
+llama-swap is a light weight, transparent proxy server that provides automatic model swapping to llama.cpp's server.
 
-Features:
+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.
+
+## Features:
 
 - ✅ Easy to deploy: single binary with no dependencies
-- ✅ Single yaml configuration file
-- ✅ Automatic switching between models
-- ✅ Full control over llama.cpp server settings per model
-- ✅ OpenAI API support (`v1/completions` and `v1/chat/completions`)
+- ✅ Easy to config: single yaml file
+- ✅ On-demand model switching
+- ✅ Full control over server settings per model
+- ✅ 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))
 - ✅ Multiple GPU support
+- ✅ Docker and Podman support
 - ✅ Run multiple models at once with `profiles`
 - ✅ 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))
 
 ## config.yaml
 
@@ -25,6 +46,9 @@ llama-swap's configuration is purposefully simple.
 # 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":
@@ -60,11 +84,26 @@ 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":
+    cmd: llama-server --port 9999 -m Llama-3.2-1B-Instruct-Q4_K_M.gguf -ngl 0
+    unlisted: true
+
+  # 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:
 #  - each model must be listening on a unique address and port
-#  - the model name is in this format: "profile_name/model", like "coding/qwen"
+#  - the model name is in this format: "profile_name:model", like "coding:qwen"
 #  - the profile will load and unload all models in the profile at the same time
 profiles:
   coding:
@@ -72,33 +111,44 @@ profiles:
     - "llama"
 ```
 
-More [examples](examples/README.md) are available for different use cases.
+### Advanced 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.
+
+### Installation
 
 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
 
-The `/logs` endpoint is available to monitor what llama-swap is doing. It will send the last 10KB of logs. Useful for monitoring the output of llama-server. It also supports streaming of logs.
+Open the `http://<host>/logs` with your browser to get a web interface with streaming logs.
 
-Usage:
+Of course, CLI access is also supported:
 
 ```
 # sends up to the last 10KB of logs
 curl http://host/logs'
 
-# streams logs using chunk encoding
+# streams logs
 curl -Ns 'http://host/logs/stream'
 
+# stream and filter logs with linux pipes
+curl -Ns http://host/logs/stream | grep 'eval time'
+
 # skips history and just streams new log entries
 curl -Ns 'http://host/logs/stream?no-history'
-
-# streams logs using Server Sent Events
-curl -Ns 'http://host/logs/streamSSE'
 ```
 
 ## Systemd Unit Files
@@ -125,9 +175,3 @@ StartLimitInterval=30
 [Install]
 WantedBy=multi-user.target
 ```
-
-## Building from Source
-
-1. Install golang for your system
-1. run `make clean all`
-1. binaries will be built into `build/` directory

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:

examples/README.md

@@ -1,9 +1,6 @@
-# Example Configurations
+# Example Configs and Use Cases
 
-Learning by example is best.
-
-Here in the `examples/` folder are llama-swap configurations that can be used on your local LLM server.
-
-## List
+A collections of usecases and examples for getting the most out of llama-swap.
 
 * [Speculative Decoding](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](benchmark-snakegame/README.md) - find the optimal settings for your machine. This example demonstrates defining multiple configurations and testing which one is fastest.

examples/benchmark-snakegame/README.md

@@ -0,0 +1,123 @@
+# Optimizing Code Generation with llama-swap
+
+Finding the best mix of settings for your hardware can be time consuming. This example demonstrates using a custom configuration file to automate testing different scenarios to find the an optimal configuration.
+
+The benchmark writes a snake game in Python, TypeScript, and Swift using the Qwen 2.5 Coder models. The experiments were done using a 3090 and a P40.
+
+**Benchmark Scenarios**
+
+Three scenarios are tested:
+
+- 3090-only: Just the main model on the 3090
+- 3090-with-draft: the main and draft models on the 3090
+- 3090-P40-draft: the main model on the 3090 with the draft model offloaded to the P40
+
+**Available Devices**
+
+Use the following command to list available devices IDs for the configuration:
+
+```
+$ /mnt/nvme/llama-server/llama-server-f3252055 --list-devices
+ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
+ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
+ggml_cuda_init: found 4 CUDA devices:
+  Device 0: NVIDIA GeForce RTX 3090, compute capability 8.6, VMM: yes
+  Device 1: Tesla P40, compute capability 6.1, VMM: yes
+  Device 2: Tesla P40, compute capability 6.1, VMM: yes
+  Device 3: Tesla P40, compute capability 6.1, VMM: yes
+Available devices:
+  CUDA0: NVIDIA GeForce RTX 3090 (24154 MiB, 406 MiB free)
+  CUDA1: Tesla P40 (24438 MiB, 22942 MiB free)
+  CUDA2: Tesla P40 (24438 MiB, 24144 MiB free)
+  CUDA3: Tesla P40 (24438 MiB, 24144 MiB free)
+```
+
+**Configuration**
+
+The configuration file, `benchmark-config.yaml`, defines the three scenarios:
+
+```yaml
+models:
+  "3090-only":
+    proxy: "http://127.0.0.1:9503"
+    cmd: >
+      /mnt/nvme/llama-server/llama-server-f3252055
+      --host 127.0.0.1 --port 9503
+      --flash-attn
+      --slots
+
+      --model /mnt/nvme/models/Qwen2.5-Coder-32B-Instruct-Q4_K_M.gguf
+      -ngl 99
+      --device CUDA0
+
+      --ctx-size 32768
+      --cache-type-k q8_0 --cache-type-v q8_0
+
+  "3090-with-draft":
+    proxy: "http://127.0.0.1:9503"
+    # --ctx-size 28500 max that can fit on 3090 after draft model
+    cmd: >
+      /mnt/nvme/llama-server/llama-server-f3252055
+      --host 127.0.0.1 --port 9503
+      --flash-attn
+      --slots
+
+      --model /mnt/nvme/models/Qwen2.5-Coder-32B-Instruct-Q4_K_M.gguf
+      -ngl 99
+      --device CUDA0
+
+      --model-draft /mnt/nvme/models/Qwen2.5-Coder-0.5B-Instruct-Q8_0.gguf
+      -ngld 99
+      --draft-max 16
+      --draft-min 4
+      --draft-p-min 0.4
+      --device-draft CUDA0
+
+      --ctx-size 28500
+      --cache-type-k q8_0 --cache-type-v q8_0
+
+  "3090-P40-draft":
+    proxy: "http://127.0.0.1:9503"
+    cmd: >
+      /mnt/nvme/llama-server/llama-server-f3252055
+      --host 127.0.0.1 --port 9503
+      --flash-attn --metrics
+      --slots
+      --model /mnt/nvme/models/Qwen2.5-Coder-32B-Instruct-Q4_K_M.gguf
+      -ngl 99
+      --device CUDA0
+
+      --model-draft /mnt/nvme/models/Qwen2.5-Coder-0.5B-Instruct-Q8_0.gguf
+      -ngld 99
+      --draft-max 16
+      --draft-min 4
+      --draft-p-min 0.4
+      --device-draft CUDA1
+
+      --ctx-size 32768
+      --cache-type-k q8_0 --cache-type-v q8_0
+```
+
+> Note in the `3090-with-draft` scenario the `--ctx-size` had to be reduced from 32768 to to accommodate the draft model.
+
+
+**Running the Benchmark**
+
+To run the benchmark, execute the following commands:
+
+1. `llama-swap -config benchmark-config.yaml`
+1. `./run-benchmark.sh http://localhost:8080 "3090-only" "3090-with-draft" "3090-P40-draft"`
+
+The [benchmark script](run-benchmark.sh) generates a CSV output of the results, which can be converted to a Markdown table for readability.
+
+**Results (tokens/second)**
+
+| model           | python | typescript | swift |
+|-----------------|--------|------------|-------|
+| 3090-only       | 34.03  | 34.01      | 34.01 |
+| 3090-with-draft | 106.65 | 70.48      | 57.89 |
+| 3090-P40-draft  | 81.54  | 60.35      | 46.50 |
+
+Many different factors, like the programming language, can have big impacts on the performance gains. However, with a custom configuration file for benchmarking it is easy to test the different variations to discover what's best for your hardware.
+
+Happy coding!

examples/benchmark-snakegame/run-benchmark.sh

@@ -0,0 +1,40 @@
+#!/usr/bin/env bash
+
+# This script generates a CSV file showing the token/second for generating a Snake Game in python, typescript and swift
+# It was created to test the effects of speculative decoding and the various draft settings on performance.
+#
+# Writing code with a low temperature seems to provide fairly consistent logic.
+#
+# Usage: ./benchmark.sh <url> <model1> [model2 ...]
+# Example: ./benchmark.sh http://localhost:8080 model1 model2
+
+if [ "$#" -lt 2 ]; then
+    echo "Usage: $0 <url> <model1> [model2 ...]"
+    exit 1
+fi
+
+url=$1; shift
+
+echo "model,python,typescript,swift"
+
+for model in "$@"; do
+
+    echo -n "$model,"
+
+    for lang in "python" "typescript" "swift"; do
+        # expects a llama.cpp after PR https://github.com/ggerganov/llama.cpp/pull/10548
+        # (Dec 3rd/2024)
+        time=$(curl -s --url "$url/v1/chat/completions" -d "{\"messages\": [{\"role\": \"system\", \"content\": \"you only write code.\"}, {\"role\": \"user\", \"content\": \"write snake game in $lang\"}], \"top_k\": 1, \"timings_per_token\":true, \"model\":\"$model\"}" | jq -r .timings.predicted_per_second)
+
+        if [ $? -ne 0 ]; then
+            time="error"
+            exit 1
+        fi
+
+        if [ "$lang" != "swift" ]; then
+            printf "%0.2f tps," $time
+        else
+            printf "%0.2f tps\n" $time
+        fi
+    done
+done

go.mod

@@ -20,6 +20,7 @@ require (
 	github.com/go-playground/universal-translator v0.18.1 // indirect
 	github.com/go-playground/validator/v10 v10.20.0 // indirect
 	github.com/goccy/go-json v0.10.2 // indirect
+	github.com/google/shlex v0.0.0-20191202100458-e7afc7fbc510 // indirect
 	github.com/json-iterator/go v1.1.12 // indirect
 	github.com/klauspost/cpuid/v2 v2.2.7 // indirect
 	github.com/leodido/go-urn v1.4.0 // indirect
@@ -31,9 +32,9 @@ require (
 	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

@@ -24,6 +24,8 @@ github.com/go-playground/validator/v10 v10.20.0/go.mod h1:dbuPbCMFw/DrkbEynArYaC
 github.com/goccy/go-json v0.10.2 h1:CrxCmQqYDkv1z7lO7Wbh2HN93uovUHgrECaO5ZrCXAU=
 github.com/goccy/go-json v0.10.2/go.mod h1:6MelG93GURQebXPDq3khkgXZkazVtN9CRI+MGFi0w8I=
 github.com/google/gofuzz v1.0.0/go.mod h1:dBl0BpW6vV/+mYPU4Po3pmUjxk6FQPldtuIdl/M65Eg=
+github.com/google/shlex v0.0.0-20191202100458-e7afc7fbc510 h1:El6M4kTTCOh6aBiKaUGG7oYTSPP8MxqL4YI3kZKwcP4=
+github.com/google/shlex v0.0.0-20191202100458-e7afc7fbc510/go.mod h1:pupxD2MaaD3pAXIBCelhxNneeOaAeabZDe5s4K6zSpQ=
 github.com/json-iterator/go v1.1.12 h1:PV8peI4a0ysnczrg+LtxykD8LfKY9ML6u2jnxaEnrnM=
 github.com/json-iterator/go v1.1.12/go.mod h1:e30LSqwooZae/UwlEbR2852Gd8hjQvJoHmT4TnhNGBo=
 github.com/klauspost/cpuid/v2 v2.0.9/go.mod h1:FInQzS24/EEf25PyTYn52gqo7WaD8xa0213Md/qVLRg=
@@ -64,14 +66,22 @@ 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/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

@@ -5,6 +5,7 @@ import (
 	"os"
 	"strings"
 
+	"github.com/google/shlex"
 	"gopkg.in/yaml.v3"
 )
 
@@ -15,6 +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) {
@@ -23,6 +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"`
 
@@ -81,7 +84,10 @@ func SanitizeCommand(cmdStr string) ([]string, error) {
 	cmdStr = strings.ReplaceAll(cmdStr, "\\\n", " ")
 
 	// Split the command into arguments
-	args := strings.Fields(cmdStr)
+	args, err := shlex.Split(cmdStr)
+	if err != nil {
+		return nil, err
+	}
 
 	// Ensure the command is not empty
 	if len(args) == 0 {

proxy/config_test.go

@@ -148,17 +148,26 @@ func TestConfig_FindConfig(t *testing.T) {
 }
 
 func TestConfig_SanitizeCommand(t *testing.T) {
-	// Test a simple command
-	args, err := SanitizeCommand("python model1.py")
-	assert.NoError(t, err)
-	assert.Equal(t, []string{"python", "model1.py"}, args)
 
 	// Test a command with spaces and newlines
-	args, err = SanitizeCommand(`python model1.py \
-    --arg1 value1 \
-    --arg2 value2`)
+	args, err := SanitizeCommand(`python model1.py \
+    -a "double quotes" \
+    --arg2 'single quotes'
+	-s
+	--arg3 123 \
+	--arg4 '"string in string"'
+	-c "'single quoted'"
+	`)
 	assert.NoError(t, err)
-	assert.Equal(t, []string{"python", "model1.py", "--arg1", "value1", "--arg2", "value2"}, args)
+	assert.Equal(t, []string{
+		"python", "model1.py",
+		"-a", "double quotes",
+		"--arg2", "single quotes",
+		"-s",
+		"--arg3", "123",
+		"--arg4", `"string in string"`,
+		"-c", `'single quoted'`,
+	}, args)
 
 	// Test an empty command
 	args, err = SanitizeCommand("")

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

@@ -0,0 +1,145 @@
+<!DOCTYPE html>
+<html lang="en">
+<head>
+    <meta charset="UTF-8">
+    <meta name="viewport" content="width=device-width, initial-scale=1.0">
+    <title>Logs</title>
+    <style>
+        body {
+            margin: 0;
+            height: 100vh;
+            display: flex;
+            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: 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>
+    <div id="log-controls">
+        <input type="text" id="filter-input" placeholder="regex filter">
+        <button id="clear-button">clear</button>
+    </div>
+    <script>
+        const logStream = document.getElementById('log-stream');
+        const filterInput = document.getElementById('filter-input');
+        var logData = "";
+        let regexFilter = null;
+
+        function setupEventSource() {
+            if (typeof(EventSource) !== "undefined") {
+                const eventSource = new EventSource("/logs/streamSSE");
+
+                eventSource.onmessage = function(event) {
+                    logData += event.data;
+                    render()
+                };
+
+                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(time.Second)
 		}
 	}
 
@@ -122,14 +223,18 @@ func (p *Process) start() error {
 		// start a goroutine to check every second if
 		// the process should be stopped
 		go func() {
-			ticker := time.NewTicker(time.Second)
-			defer ticker.Stop()
 			maxDuration := time.Duration(p.config.UnloadAfter) * time.Second
 
-			for {
-				<-ticker.C
+			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
 				}
@@ -137,159 +242,142 @@ func (p *Process) start() error {
 		}()
 	}
 
-	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)
-	defer p.inFlightRequests.Done()
+	// 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
 		}
 	}
 
-	p.lastRequestHandled = time.Now()
-
 	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")
@@ -79,29 +109,69 @@ 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()
 
-	req := httptest.NewRequest("GET", "/test", nil)
+	// this should take 4 seconds
+	req1 := httptest.NewRequest("GET", "/slow-respond?echo=1234&delay=1000ms", nil)
+	req2 := httptest.NewRequest("GET", "/test", nil)
+
 	w := httptest.NewRecorder()
 
-	// Proxy the request (auto start)
-	process.ProxyRequest(w, req)
+	// Proxy the request (auto start) with a slow response that takes longer than config.UnloadAfter
+	process.ProxyRequest(w, req1)
 
+	t.Log("sending slow first request (4 seconds)")
+	assert.Equal(t, http.StatusOK, w.Code, "Expected status code %d, got %d", http.StatusOK, w.Code)
+	assert.Contains(t, w.Body.String(), "1234")
+	assert.Equal(t, StateReady, process.CurrentState())
+
+	// ensure the TTL timeout does not race slow requests (see issue #25)
+	t.Log("sending second request (1 second)")
+	time.Sleep(time.Second)
+	w = httptest.NewRecorder()
+	process.ProxyRequest(w, req2)
 	assert.Equal(t, http.StatusOK, w.Code, "Expected status code %d, got %d", http.StatusOK, w.Code)
 	assert.Contains(t, w.Body.String(), expectedMessage)
-
 	assert.Equal(t, StateReady, process.CurrentState())
 
 	// wait 5 seconds
+	t.Log("sleep 5 seconds and check if unloaded")
 	time.Sleep(5 * time.Second)
 	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() {
-		t.Skip("skipping long test")
+		t.Skip("skipping slow test")
 	}
 
 	expectedMessage := "12345"
@@ -151,3 +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

@@ -6,6 +6,7 @@ import (
 	"fmt"
 	"io"
 	"net/http"
+	"sort"
 	"strconv"
 	"strings"
 	"sync"
@@ -14,6 +15,10 @@ import (
 	"github.com/gin-gonic/gin"
 )
 
+const (
+	PROFILE_SPLIT_CHAR = ":"
+)
+
 type ProxyManager struct {
 	sync.Mutex
 
@@ -31,11 +36,63 @@ 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)
 
@@ -44,7 +101,33 @@ 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("/", 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()
@@ -73,16 +156,45 @@ 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",
@@ -94,9 +206,13 @@ func (pm *ProxyManager) listModelsHandler(c *gin.Context) {
 	// Set the Content-Type header to application/json
 	c.Header("Content-Type", "application/json")
 
+	if origin := c.Request.Header.Get("Origin"); origin != "" {
+		c.Header("Access-Control-Allow-Origin", origin)
+	}
+
 	// 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
 	}
 }
@@ -105,16 +221,16 @@ func (pm *ProxyManager) swapModel(requestedModel string) (*Process, error) {
 	pm.Lock()
 	defer pm.Unlock()
 
-	// Check if requestedModel contains a /
-	groupName, modelName := "", requestedModel
-	if idx := strings.Index(requestedModel, "/"); idx != -1 {
-		groupName = requestedModel[:idx]
+	// Check if requestedModel contains a PROFILE_SPLIT_CHAR
+	profileName, modelName := "", requestedModel
+	if idx := strings.Index(requestedModel, PROFILE_SPLIT_CHAR); idx != -1 {
+		profileName = requestedModel[:idx]
 		modelName = requestedModel[idx+1:]
 	}
 
-	if groupName != "" {
-		if _, found := pm.config.Profiles[groupName]; !found {
-			return nil, fmt.Errorf("model group not found %s", groupName)
+	if profileName != "" {
+		if _, found := pm.config.Profiles[profileName]; !found {
+			return nil, fmt.Errorf("model group not found %s", profileName)
 		}
 	}
 
@@ -124,8 +240,24 @@ 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 := groupName + "/" + realModelName
+	requestedProcessKey := ProcessKeyName(profileName, realModelName)
+
 	if process, found := pm.currentProcesses[requestedProcessKey]; found {
 		return process, nil
 	}
@@ -133,25 +265,25 @@ func (pm *ProxyManager) swapModel(requestedModel string) (*Process, error) {
 	// stop all running models
 	pm.stopProcesses()
 
-	if groupName == "" {
+	if profileName == "" {
 		modelConfig, modelID, found := pm.config.FindConfig(realModelName)
 		if !found {
 			return nil, fmt.Errorf("could not find configuration for %s", realModelName)
 		}
 
 		process := NewProcess(modelID, pm.config.HealthCheckTimeout, modelConfig, pm.logMonitor)
-		processKey := groupName + "/" + modelID
+		processKey := ProcessKeyName(profileName, modelID)
 		pm.currentProcesses[processKey] = process
 	} else {
-		for _, modelName := range pm.config.Profiles[groupName] {
+		for _, modelName := range pm.config.Profiles[profileName] {
 			if realModelName, found := pm.config.RealModelName(modelName); found {
 				modelConfig, modelID, found := pm.config.FindConfig(realModelName)
 				if !found {
-					return nil, fmt.Errorf("could not find configuration for %s in group %s", realModelName, groupName)
+					return nil, fmt.Errorf("could not find configuration for %s in group %s", realModelName, profileName)
 				}
 
 				process := NewProcess(modelID, pm.config.HealthCheckTimeout, modelConfig, pm.logMonitor)
-				processKey := groupName + "/" + modelID
+				processKey := ProcessKeyName(profileName, modelID)
 				pm.currentProcesses[processKey] = process
 			}
 		}
@@ -161,25 +293,68 @@ 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"))
+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(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
+	}
+
 	var requestBody map[string]interface{}
 	if err := json.Unmarshal(bodyBytes, &requestBody); err != nil {
-		c.AbortWithError(http.StatusBadRequest, fmt.Errorf("invalid JSON"))
+		pm.sendErrorResponse(c, http.StatusBadRequest, fmt.Sprintf("invalid JSON: %s", err.Error()))
 		return
 	}
 	model, ok := requestBody["model"].(string)
 	if !ok {
-		c.AbortWithError(http.StatusBadRequest, fmt.Errorf("missing or invalid 'model' key"))
+		pm.sendErrorResponse(c, http.StatusBadRequest, "missing or invalid 'model' key")
 		return
 	}
 
 	if process, err := pm.swapModel(model); err != nil {
-		c.AbortWithError(http.StatusNotFound, fmt.Errorf("unable to swap to model, %s", err.Error()))
+		pm.sendErrorResponse(c, http.StatusNotFound, fmt.Sprintf("unable to swap to model, %s", err.Error()))
 		return
 	} else {
 		c.Request.Body = io.NopCloser(bytes.NewBuffer(bodyBytes))
@@ -192,12 +367,16 @@ 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 ProcessKeyName(groupName, modelName string) string {
+	return groupName + PROFILE_SPLIT_CHAR + modelName
 }

proxy/proxymanager_loghandlers.go

@@ -3,17 +3,37 @@ package proxy
 import (
 	"fmt"
 	"net/http"
+	"strings"
 
 	"github.com/gin-gonic/gin"
 )
 
 func (pm *ProxyManager) sendLogsHandlers(c *gin.Context) {
-	c.Header("Content-Type", "text/plain")
-	history := pm.logMonitor.GetHistory()
-	_, err := c.Writer.Write(history)
-	if err != nil {
-		c.AbortWithError(http.StatusInternalServerError, err)
-		return
+
+	accept := c.GetHeader("Accept")
+	if strings.Contains(accept, "text/html") {
+		// Set the Content-Type header to text/html
+		c.Header("Content-Type", "text/html")
+
+		// Write the embedded HTML content to the response
+		logsHTML, err := getHTMLFile("logs.html")
+		if err != nil {
+			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 {
+		c.Header("Content-Type", "text/plain")
+		history := pm.logMonitor.GetHistory()
+		_, err := c.Writer.Write(history)
+		if err != nil {
+			c.AbortWithError(http.StatusInternalServerError, err)
+			return
+		}
 	}
 }
 
@@ -28,7 +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
 	}
 
@@ -38,11 +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()
 		}
 	}
@@ -53,7 +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

@@ -2,6 +2,7 @@ package proxy
 
 import (
 	"bytes"
+	"encoding/json"
 	"fmt"
 	"net/http"
 	"net/http/httptest"
@@ -33,7 +34,7 @@ func TestProxyManager_SwapProcessCorrectly(t *testing.T) {
 		assert.Equal(t, http.StatusOK, w.Code)
 		assert.Contains(t, w.Body.String(), modelName)
 
-		_, exists := proxy.currentProcesses["/"+modelName]
+		_, exists := proxy.currentProcesses[ProcessKeyName("", modelName)]
 		assert.True(t, exists, "expected %s key in currentProcesses", modelName)
 
 	}
@@ -43,21 +44,31 @@ func TestProxyManager_SwapProcessCorrectly(t *testing.T) {
 }
 
 func TestProxyManager_SwapMultiProcess(t *testing.T) {
+
+	model1 := "path1/model1"
+	model2 := "path2/model2"
+
+	profileModel1 := ProcessKeyName("test", model1)
+	profileModel2 := ProcessKeyName("test", model2)
+
 	config := &Config{
 		HealthCheckTimeout: 15,
 		Models: map[string]ModelConfig{
-			"model1": getTestSimpleResponderConfig("model1"),
-			"model2": getTestSimpleResponderConfig("model2"),
+			model1: getTestSimpleResponderConfig("model1"),
+			model2: getTestSimpleResponderConfig("model2"),
 		},
 		Profiles: map[string][]string{
-			"test": {"model1", "model2"},
+			"test": {model1, model2},
 		},
 	}
 
 	proxy := New(config)
 	defer proxy.StopProcesses()
 
-	for modelID, requestedModel := range map[string]string{"model1": "test/model1", "model2": "test/model2"} {
+	for modelID, requestedModel := range map[string]string{
+		"model1": profileModel1,
+		"model2": profileModel2,
+	} {
 		reqBody := fmt.Sprintf(`{"model":"%s"}`, requestedModel)
 		req := httptest.NewRequest("POST", "/v1/chat/completions", bytes.NewBufferString(reqBody))
 		w := httptest.NewRecorder()
@@ -69,11 +80,11 @@ func TestProxyManager_SwapMultiProcess(t *testing.T) {
 
 	// make sure there's two loaded models
 	assert.Len(t, proxy.currentProcesses, 2)
-	_, exists := proxy.currentProcesses["test/model1"]
-	assert.True(t, exists, "expected test/model1 key in currentProcesses")
+	_, exists := proxy.currentProcesses[profileModel1]
+	assert.True(t, exists, "expected "+profileModel1+" key in currentProcesses")
 
-	_, exists = proxy.currentProcesses["test/model2"]
-	assert.True(t, exists, "expected test/model2 key in currentProcesses")
+	_, exists = proxy.currentProcesses[profileModel2]
+	assert.True(t, exists, "expected "+profileModel2+" key in currentProcesses")
 }
 
 // When a request for a different model comes in ProxyManager should wait until
@@ -131,3 +142,165 @@ func TestProxyManager_SwapMultiProcessParallelRequests(t *testing.T) {
 		assert.Equal(t, key, result)
 	}
 }
+
+func TestProxyManager_ListModelsHandler(t *testing.T) {
+	config := &Config{
+		HealthCheckTimeout: 15,
+		Models: map[string]ModelConfig{
+			"model1": getTestSimpleResponderConfig("model1"),
+			"model2": getTestSimpleResponderConfig("model2"),
+			"model3": getTestSimpleResponderConfig("model3"),
+		},
+	}
+
+	proxy := New(config)
+
+	// Create a test request
+	req := httptest.NewRequest("GET", "/v1/models", nil)
+	req.Header.Add("Origin", "i-am-the-origin")
+	w := httptest.NewRecorder()
+
+	// Call the listModelsHandler
+	proxy.HandlerFunc(w, req)
+
+	// Check the response status code
+	assert.Equal(t, http.StatusOK, w.Code)
+
+	// Check for Access-Control-Allow-Origin
+	assert.Equal(t, req.Header.Get("Origin"), w.Result().Header.Get("Access-Control-Allow-Origin"))
+
+	// Parse the JSON response
+	var response struct {
+		Data []map[string]interface{} `json:"data"`
+	}
+	if err := json.Unmarshal(w.Body.Bytes(), &response); err != nil {
+		t.Fatalf("Failed to parse JSON response: %v", err)
+	}
+
+	// Check the number of models returned
+	assert.Len(t, response.Data, 3)
+
+	// Check the details of each model
+	expectedModels := map[string]struct{}{
+		"model1": {},
+		"model2": {},
+		"model3": {},
+	}
+
+	for _, model := range response.Data {
+		modelID, ok := model["id"].(string)
+		assert.True(t, ok, "model ID should be a string")
+		_, exists := expectedModels[modelID]
+		assert.True(t, exists, "unexpected model ID: %s", modelID)
+		delete(expectedModels, modelID)
+
+		object, ok := model["object"].(string)
+		assert.True(t, ok, "object should be a string")
+		assert.Equal(t, "model", object)
+
+		created, ok := model["created"].(float64)
+		assert.True(t, ok, "created should be a number")
+		assert.Greater(t, created, float64(0)) // Assuming the timestamp is positive
+
+		ownedBy, ok := model["owned_by"].(string)
+		assert.True(t, ok, "owned_by should be a string")
+		assert.Equal(t, "llama-swap", ownedBy)
+	}
+
+	// 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()
+}