Improve handling of process that do not handle SIGTERM (#38)

- Process TTL goroutine did not have a return after .Stop()
- Improve logging
- Add test TestProcess_LowTTLValue to measure SIGTERM error rate

.gitignore

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

Makefile

@@ -9,8 +9,8 @@ ifneq ($(shell git status --porcelain),)
     GIT_HASH := $(GIT_HASH)+
 endif
 
-# Get the build number from the commit count on the main branch
-COMMIT_COUNT := $(shell git rev-list --count HEAD)
+# 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
@@ -28,12 +28,12 @@ test-all:
 # Build OSX binary
 mac:
 	@echo "Building Mac binary..."
-	GOOS=darwin GOARCH=arm64 go build -ldflags="-X main.GIT_HASH=${GIT_HASH} -X main.COMMIT_COUNT=${COMMIT_COUNT}" -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 -ldflags="-X main.GIT_HASH=${GIT_HASH} -X main.COMMIT_COUNT=${COMMIT_COUNT}" -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:
@@ -52,9 +52,12 @@ release:
 		echo "Error: There are unstaged changes. Please commit or stash your changes before creating a release tag." >&2; \
 		exit 1; \
 	fi
-	@echo "Creating release tag v$(COMMIT_COUNT)..."
-	git tag v$(COMMIT_COUNT)
-	git push origin v$(COMMIT_COUNT)
+
+# 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

@@ -3,31 +3,38 @@
 ![llama-swap header image](header.jpeg)
 
 # Introduction
-llama-swap is an OpenAI API compatible server that gives you complete control over how you use your hardware. It automatically swaps to the configuration of your choice for serving a model. Since [llama.cpp's server](https://github.com/ggerganov/llama.cpp/tree/master/examples/server) can't swap models, let's swap the server instead!
+llama-swap 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
+- ✅ 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`)
+- ✅ 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
 - ✅ Run multiple models at once with `profiles`
 - ✅ Remote log monitoring at `/log`
 - ✅ Automatic unloading of models from GPUs after timeout
-- ✅ Use any local server that provides an OpenAI compatible API (llama.cpp, vllm, tabblyAPI, etc)
-
-## 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
+- ✅ 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
 
@@ -38,6 +45,9 @@ 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":
@@ -73,6 +83,12 @@ 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:
@@ -85,15 +101,26 @@ 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
 
 Open the `http://<host>/logs` with your browser to get a web interface with streaming logs.

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 +29,31 @@ 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
+
+
   "simple":
     # example of setting environment variables
     env:
@@ -33,6 +61,7 @@ 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 +71,11 @@ 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:

go.mod

@@ -33,7 +33,7 @@ require (
 	github.com/ugorji/go/codec v1.2.12 // indirect
 	golang.org/x/arch v0.8.0 // indirect
 	golang.org/x/crypto v0.31.0 // indirect
-	golang.org/x/net v0.25.0 // 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

@@ -70,6 +70,8 @@ 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=

llama-swap.go

@@ -9,9 +9,9 @@ import (
 	"github.com/mostlygeek/llama-swap/proxy"
 )
 
-// see Makefile which injects new values at build time
-var GIT_HASH string = "abcd1234"
-var COMMIT_COUNT string = "0-dev"
+var version string = "0"
+var commit string = "abcd1234"
+var date = "unknown"
 
 func main() {
 	// Define a command-line flag for the port
@@ -22,7 +22,7 @@ func main() {
 	flag.Parse() // Parse the command-line flags
 
 	if *showVersion {
-		fmt.Printf("version: v%s (%s)\n", COMMIT_COUNT, GIT_HASH)
+		fmt.Printf("version: %s (%s), built at %s\n", version, commit, date)
 		os.Exit(0)
 	}
 

misc/test-rerank/README.md

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

misc/test-rerank/reranker-test.json

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

proxy/config.go

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

proxy/html/index.html

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

proxy/html/logs.html

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

proxy/html_files.go

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

proxy/logMonitor.go

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

proxy/process.go

@@ -125,12 +125,17 @@ func (p *Process) start() error {
 			maxDuration := time.Duration(p.config.UnloadAfter) * time.Second
 
 			for range time.Tick(time.Second) {
+				if p.state != StateReady {
+					return
+				}
+
 				// wait for all inflight requests to complete and ticker
 				p.inFlightRequests.Wait()
 
 				if time.Since(p.lastRequestHandled) > maxDuration {
-					fmt.Fprintf(p.logMonitor, "!!! Unloading model %s, TTL of %d reached.\n", p.ID, p.config.UnloadAfter)
+					fmt.Fprintf(p.logMonitor, "!!! Unloading model %s, TTL of %ds reached.\n", p.ID, p.config.UnloadAfter)
 					p.Stop()
+					return
 				}
 			}
 		}()
@@ -161,26 +166,27 @@ func (p *Process) Stop() {
 	// Pretty sure this stopping code needs some work for windows and
 	// 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()
 	}()
 
+	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, "XXX Process for %s timed out waiting to stop, sending SIGKILL to PID: %d\n", p.ID, p.cmd.Process.Pid)
 		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)
 			}
 		}
 	}

proxy/process_test.go

@@ -67,7 +67,6 @@ func TestProcess_BrokenModelConfig(t *testing.T) {
 	assert.Contains(t, w.Body.String(), "unable to start process")
 }
 
-// test that the process unloads after the TTL
 func TestProcess_UnloadAfterTTL(t *testing.T) {
 	if testing.Short() {
 		t.Skip("skipping long auto unload TTL test")
@@ -79,7 +78,7 @@ func TestProcess_UnloadAfterTTL(t *testing.T) {
 	config.UnloadAfter = 3 // seconds
 	assert.Equal(t, 3, config.UnloadAfter)
 
-	process := NewProcess("ttl", 2, config, NewLogMonitorWriter(io.Discard))
+	process := NewProcess("ttl_test", 2, config, NewLogMonitorWriter(io.Discard))
 	defer process.Stop()
 
 	// this should take 4 seconds
@@ -111,6 +110,33 @@ func TestProcess_UnloadAfterTTL(t *testing.T) {
 	assert.Equal(t, StateStopped, process.CurrentState())
 }
 
+func TestProcess_LowTTLValue(t *testing.T) {
+	if true { // change this code to run this ...
+		t.Skip("skipping test, edit process_test.go to run it ")
+	}
+
+	config := getTestSimpleResponderConfig("fast_ttl")
+	assert.Equal(t, 0, config.UnloadAfter)
+	config.UnloadAfter = 1 // second
+	assert.Equal(t, 1, config.UnloadAfter)
+
+	process := NewProcess("ttl", 2, config, NewLogMonitorWriter(os.Stdout))
+	defer process.Stop()
+
+	for i := 0; i < 100; i++ {
+		t.Logf("Waiting before sending request %d", i)
+		time.Sleep(1500 * time.Millisecond)
+
+		expected := fmt.Sprintf("echo=test_%d", i)
+		req := httptest.NewRequest("GET", fmt.Sprintf("/slow-respond?echo=%s&delay=50ms", expected), nil)
+		w := httptest.NewRecorder()
+		process.ProxyRequest(w, req)
+		assert.Equal(t, http.StatusOK, w.Code)
+		assert.Contains(t, w.Body.String(), expected)
+	}
+
+}
+
 // issue #19
 func TestProcess_HTTPRequestsHaveTimeToFinish(t *testing.T) {
 	if testing.Short() {

proxy/proxymanager.go

@@ -6,6 +6,7 @@ import (
 	"fmt"
 	"io"
 	"net/http"
+	"sort"
 	"strconv"
 	"strings"
 	"sync"
@@ -35,11 +36,50 @@ 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,
+			)
+		})
+	}
+
+	// Set up routes using the Gin engine
+	pm.ginEngine.POST("/v1/chat/completions", pm.proxyOAIHandler)
 	// Support legacy /v1/completions api, see issue #12
-	pm.ginEngine.POST("/v1/completions", pm.proxyChatRequestHandler)
+	pm.ginEngine.POST("/v1/completions", pm.proxyOAIHandler)
+
+	// Support embeddings
+	pm.ginEngine.POST("/v1/embeddings", pm.proxyOAIHandler)
+	pm.ginEngine.POST("/v1/rerank", pm.proxyOAIHandler)
+
+	// Support audio/speech endpoint
+	pm.ginEngine.POST("/v1/audio/speech", pm.proxyOAIHandler)
 
 	pm.ginEngine.GET("/v1/models", pm.listModelsHandler)
 
@@ -48,7 +88,33 @@ 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()
@@ -86,7 +152,11 @@ 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",
@@ -104,7 +174,7 @@ func (pm *ProxyManager) listModelsHandler(c *gin.Context) {
 
 	// Encode the data as JSON and write it to the response writer
 	if err := json.NewEncoder(c.Writer).Encode(map[string]interface{}{"data": data}); err != nil {
-		c.AbortWithError(http.StatusInternalServerError, fmt.Errorf("error encoding JSON"))
+		pm.sendErrorResponse(c, http.StatusInternalServerError, fmt.Sprintf("error encoding JSON %s", err.Error()))
 		return
 	}
 }
@@ -113,7 +183,7 @@ func (pm *ProxyManager) swapModel(requestedModel string) (*Process, error) {
 	pm.Lock()
 	defer pm.Unlock()
 
-	// Check if requestedModel contains a /
+	// Check if requestedModel contains a PROFILE_SPLIT_CHAR
 	profileName, modelName := "", requestedModel
 	if idx := strings.Index(requestedModel, PROFILE_SPLIT_CHAR); idx != -1 {
 		profileName = requestedModel[:idx]
@@ -132,6 +202,21 @@ func (pm *ProxyManager) swapModel(requestedModel string) (*Process, error) {
 		return nil, fmt.Errorf("could not find modelID for %s", requestedModel)
 	}
 
+	// check if model is part of the profile
+	if profileName != "" {
+		found := false
+		for _, item := range pm.config.Profiles[profileName] {
+			if item == realModelName {
+				found = true
+				break
+			}
+		}
+
+		if !found {
+			return nil, fmt.Errorf("model %s part of profile %s", realModelName, profileName)
+		}
+	}
+
 	// exit early when already running, otherwise stop everything and swap
 	requestedProcessKey := ProcessKeyName(profileName, realModelName)
 
@@ -170,25 +255,68 @@ 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))
@@ -201,14 +329,14 @@ 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 {

proxy/proxymanager_loghandlers.go

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

proxy/proxymanager_test.go

@@ -210,3 +210,47 @@ func TestProxyManager_ListModelsHandler(t *testing.T) {
 	// Ensure all expected models were returned
 	assert.Empty(t, expectedModels, "not all expected models were returned")
 }
+
+func TestProxyManager_ProfileNonMember(t *testing.T) {
+
+	model1 := "path1/model1"
+	model2 := "path2/model2"
+
+	profileMemberName := ProcessKeyName("test", model1)
+	profileNonMemberName := ProcessKeyName("test", model2)
+
+	config := &Config{
+		HealthCheckTimeout: 15,
+		Models: map[string]ModelConfig{
+			model1: getTestSimpleResponderConfig("model1"),
+			model2: getTestSimpleResponderConfig("model2"),
+		},
+		Profiles: map[string][]string{
+			"test": {model1},
+		},
+	}
+
+	proxy := New(config)
+	defer proxy.StopProcesses()
+
+	// actual member of profile
+	{
+		reqBody := fmt.Sprintf(`{"model":"%s"}`, profileMemberName)
+		req := httptest.NewRequest("POST", "/v1/chat/completions", bytes.NewBufferString(reqBody))
+		w := httptest.NewRecorder()
+
+		proxy.HandlerFunc(w, req)
+		assert.Equal(t, http.StatusOK, w.Code)
+		assert.Contains(t, w.Body.String(), "model1")
+	}
+
+	// actual model, but non-member will 404
+	{
+		reqBody := fmt.Sprintf(`{"model":"%s"}`, profileNonMemberName)
+		req := httptest.NewRequest("POST", "/v1/chat/completions", bytes.NewBufferString(reqBody))
+		w := httptest.NewRecorder()
+
+		proxy.HandlerFunc(w, req)
+		assert.Equal(t, http.StatusNotFound, w.Code)
+	}
+}