Add /upstream endpoint (#30)

* remove catch-all route to upstream proxy (it was broken anyways)
* add /upstream/:model_id to swap and route to upstream path
* add /upstream HTML endpoint and unlisted option
* add /upstream endpoint to show a list of available models
* add `unlisted` configuration option to omit a model from /v1/models and /upstream lists
* add favicon.ico

.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 +2,33 @@
 
 ![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 an OpenAI API compatible server that gives you complete control over how you use your hardware. It automatically swaps to the configuration of your choice for serving a model. Since [llama.cpp's server](https://github.com/ggerganov/llama.cpp/tree/master/examples/server) can't swap models, let's swap the server instead!
 
 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
+- ✅ Easy to config: single yaml file
+- ✅ On-demand model switching
+- ✅ Full control over server settings per model
 - ✅ OpenAI API support (`v1/completions` and `v1/chat/completions`)
 - ✅ Multiple GPU support
 - ✅ Run multiple models at once with `profiles`
 - ✅ Remote log monitoring at `/log`
 - ✅ Automatic unloading of models from GPUs after timeout
+- ✅ Use any local OpenAI compatible server (llama.cpp, vllm, tabblyAPI, etc)
+- ✅ Direct access to proxied upstream HTTP server via `/upstream/:model_id`
+
+## Releases
+
+Builds for Linux and OSX are available on the [Releases](https://github.com/mostlygeek/llama-swap/releases) page.
+
+### 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
 
 ## config.yaml
 
@@ -60,11 +74,17 @@ 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
+
 # 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:
@@ -83,22 +103,22 @@ More [examples](examples/README.md) are available for different use cases.
 
 ## 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 +145,3 @@ 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

@@ -33,6 +33,7 @@ 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 +43,11 @@ 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/crypto v0.31.0 // 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/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 +66,20 @@ 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/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

@@ -9,13 +9,23 @@ import (
 	"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)

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) {
@@ -81,7 +83,10 @@ 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/logs.html

@@ -0,0 +1,53 @@
+<!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-stream {
+            flex: 1;
+            margin: 1em;
+            padding: 10px;
+            background: #f4f4f4;
+            overflow-y: auto;
+            white-space: pre-wrap; /* Ensures line wrapping */
+            word-wrap: break-word; /* Ensures long words wrap */
+        }
+    </style>
+</head>
+<body>
+    <pre id="log-stream">Waiting for logs...
+</pre>
+
+    <script>
+        // Establish an EventSource connection to the SSE endpoint
+        if (typeof(EventSource) !== "undefined") {
+            const eventSource = new EventSource("/logs/streamSSE");
+
+            eventSource.onmessage = function(event) {
+                // Append the new log message to the <pre> element
+                const logStream = document.getElementById('log-stream');
+
+                logStream.textContent += event.data;
+
+                // Auto-scroll to the bottom
+                logStream.scrollTop = logStream.scrollHeight;
+            };
+
+            eventSource.onerror = function(err) {
+                console.error("EventSource failed:", err);
+            };
+        } else {
+            console.error("SSE not supported by this browser.");
+        }
+    </script>
+</body>
+</html>

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

@@ -122,17 +122,20 @@ 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
-				if time.Since(p.lastRequestHandled) > maxDuration {
-					fmt.Fprintf(p.logMonitor, "!!! Unloading model %s, TTL of %d reached.\n", p.ID, p.config.UnloadAfter)
-					p.Stop()
+			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 %ds reached.\n", p.ID, p.config.UnloadAfter)
+					p.Stop()
+				}
 			}
 		}()
 	}
@@ -163,25 +166,25 @@ func (p *Process) Stop() {
 	// will be a source of pain in the future.
 
 	p.cmd.Process.Signal(syscall.SIGTERM)
-	ctx, cancel := context.WithTimeout(context.Background(), 5*time.Second)
+	sigtermTimeout, cancel := context.WithTimeout(context.Background(), 5*time.Second)
 	defer cancel()
 
-	done := make(chan error, 1)
+	sigtermNormal := make(chan error, 1)
 	go func() {
-		done <- p.cmd.Wait()
+		sigtermNormal <- p.cmd.Wait()
 	}()
 
 	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 for %s timed out waiting to stop\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)
+				fmt.Fprintf(p.logMonitor, "!!! process for %s stopped with error > %v\n", p.ID, err)
 			}
 		}
 	}
@@ -275,7 +278,11 @@ func (p *Process) checkHealthEndpoint(ctxFromStart context.Context) error {
 func (p *Process) ProxyRequest(w http.ResponseWriter, r *http.Request) {
 
 	p.inFlightRequests.Add(1)
-	defer p.inFlightRequests.Done()
+
+	defer func() {
+		p.lastRequestHandled = time.Now()
+		p.inFlightRequests.Done()
+	}()
 
 	if p.CurrentState() != StateReady {
 		if err := p.start(); err != nil {
@@ -285,8 +292,6 @@ func (p *Process) ProxyRequest(w http.ResponseWriter, r *http.Request) {
 		}
 	}
 
-	p.lastRequestHandled = time.Now()
-
 	proxyTo := p.config.Proxy
 	client := &http.Client{}
 	req, err := http.NewRequest(r.Method, proxyTo+r.URL.String(), r.Body)

proxy/process_test.go

@@ -82,18 +82,31 @@ func TestProcess_UnloadAfterTTL(t *testing.T) {
 	process := NewProcess("ttl", 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())
 }
@@ -101,7 +114,7 @@ func TestProcess_UnloadAfterTTL(t *testing.T) {
 // issue #19
 func TestProcess_HTTPRequestsHaveTimeToFinish(t *testing.T) {
 	if testing.Short() {
-		t.Skip("skipping long test")
+		t.Skip("skipping slow test")
 	}
 
 	expectedMessage := "12345"

proxy/proxymanager.go

@@ -2,10 +2,12 @@ package proxy
 
 import (
 	"bytes"
+	"embed"
 	"encoding/json"
 	"fmt"
 	"io"
 	"net/http"
+	"sort"
 	"strconv"
 	"strings"
 	"sync"
@@ -14,6 +16,19 @@ import (
 	"github.com/gin-gonic/gin"
 )
 
+const (
+	PROFILE_SPLIT_CHAR = ":"
+)
+
+//go:embed html/favicon.ico
+var faviconData []byte
+
+//go:embed html/logs.html
+var logsHTML []byte
+
+// make sure embed is kept there by the IDE auto-package importer
+var _ = embed.FS{}
+
 type ProxyManager struct {
 	sync.Mutex
 
@@ -44,7 +59,12 @@ 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("/favicon.ico", func(c *gin.Context) {
+		c.Data(http.StatusOK, "image/x-icon", faviconData)
+	})
 
 	// Disable console color for testing
 	gin.DisableConsoleColor()
@@ -82,7 +102,11 @@ func (pm *ProxyManager) stopProcesses() {
 
 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",
@@ -94,6 +118,10 @@ 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"))
@@ -105,16 +133,16 @@ 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)
 		}
 	}
 
@@ -125,7 +153,8 @@ func (pm *ProxyManager) swapModel(requestedModel string) (*Process, error) {
 	}
 
 	// 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 +162,25 @@ 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
 			}
 		}
@@ -161,6 +190,48 @@ func (pm *ProxyManager) swapModel(requestedModel string) (*Process, error) {
 	return pm.currentProcesses[requestedProcessKey], nil
 }
 
+func (pm *ProxyManager) proxyToUpstream(c *gin.Context) {
+	requestedModel := c.Param("model_id")
+
+	if requestedModel == "" {
+		c.AbortWithError(http.StatusBadRequest, fmt.Errorf("model id required in path"))
+		return
+	}
+
+	if process, err := pm.swapModel(requestedModel); err != nil {
+		c.AbortWithError(http.StatusNotFound, fmt.Errorf("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) proxyChatRequestHandler(c *gin.Context) {
 	bodyBytes, err := io.ReadAll(c.Request.Body)
 	if err != nil {
@@ -192,12 +263,6 @@ 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
-	}
-
-	c.AbortWithError(http.StatusBadRequest, fmt.Errorf("no strategy to handle request"))
+func ProcessKeyName(groupName, modelName string) string {
+	return groupName + PROFILE_SPLIT_CHAR + modelName
 }

proxy/proxymanager_loghandlers.go

@@ -3,17 +3,32 @@ 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
+		_, err := c.Writer.Write(logsHTML)
+		if err != nil {
+			c.AbortWithError(http.StatusInternalServerError, fmt.Errorf("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
+		}
 	}
 }
 

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 +142,71 @@ 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")
+}