change llama-swap to use goreleaser default ldflag values

- does not affect the project as llama-swap does not use the crypto
  libraries
- good practice to keep security deps updated!

.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 }}

Makefile

@@ -2,6 +2,19 @@
 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
+
+# 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
 
@@ -18,12 +31,12 @@ 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=${GIT_HASH} -X main.version=${COMMIT_COUNT} -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=${GIT_HASH} -X main.version=${COMMIT_COUNT} -X main.date=${BUILD_DATE}" -o $(BUILD_DIR)/$(APP_NAME)-linux-amd64
 
 # for testing proxy.Process
 simple-responder:
@@ -35,5 +48,16 @@ simple-responder:
 $(BUILD_DIR):
 	mkdir -p $(BUILD_DIR)
 
+# Create a new release tag
+release:
+	@echo "Checking for unstaged changes..."
+	@if [ -n "$(shell git status --porcelain)" ]; then \
+		echo "Error: There are unstaged changes. Please commit or stash your changes before creating a release tag." >&2; \
+		exit 1; \
+	fi
+	@echo "Creating release tag v$(COMMIT_COUNT)..."
+	git tag v$(COMMIT_COUNT)
+	git push origin v$(COMMIT_COUNT)
+
 # Phony targets
 .PHONY: all clean osx linux

README.md

@@ -16,6 +16,7 @@ Features:
 - ✅ 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
 

go.mod

@@ -32,9 +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/sys v0.28.0 // indirect
-	golang.org/x/text v0.15.0 // indirect
+	golang.org/x/text v0.21.0 // indirect
 	google.golang.org/protobuf v1.34.1 // indirect
 )

go.sum

@@ -66,14 +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: v%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/process.go

@@ -122,16 +122,15 @@ 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 {
+			for range time.Tick(time.Second) {
-				<-ticker.C
+				// 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)
 					p.Stop()
-					return
 				}
 			}
 		}()
@@ -275,7 +274,11 @@ 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 +288,6 @@ 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)
+	// Proxy the request (auto start) with a slow response that takes longer than config.UnloadAfter
-	process.ProxyRequest(w, req)
+	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())
 }