Compare commits

..

3 Commits

Author SHA1 Message Date
Benson Wong 0f583163f7 add /health (#211) 2025-07-30 10:37:10 -07:00
Benson Wong 7905fa9ea3 Update trigger-homebrew-update.yml [skip ci] 2025-07-30 10:13:49 -07:00
Ian Sebastian Mathew bbaf172956 add trigger to rebuild homebrew formula (#210) 2025-07-30 10:12:21 -07:00
4 changed files with 59 additions and 0 deletions
@@ -0,0 +1,24 @@
name: Trigger Homebrew Tap Update
on:
release:
types: [published]
# Allows manual triggering of the workflow
workflow_dispatch:
jobs:
trigger-tap-update:
runs-on: ubuntu-latest
steps:
- name: "Trigger tap repository update"
uses: peter-evans/repository-dispatch@v2
with:
token: ${{ secrets.TAP_REPO_PAT }}
repository: mostlygeek/homebrew-llama-swap
event-type: new-release
client-payload: |-
{
"release": {
"tag_name": "${{ github.event.release.tag_name }}"
}
}
+14
View File
@@ -122,6 +122,20 @@ $ docker run -it --rm --runtime nvidia -p 9292:8080 \
</details> </details>
## Homebrew Install (macOS/Linux)
For macOS & Linux users, `llama-swap` can be installed via [Homebrew](https://brew.sh):
```shell
# Set up tap and install formula
brew tap mostlygeek/llama-swap
brew install llama-swap
# Run llama-swap
llama-swap --config path/to/config.yaml --listen localhost:8080
```
This will install the `llama-swap` binary and make it available in your path. See the [configuration documentation](https://github.com/mostlygeek/llama-swap/wiki/Configuration)
## Bare metal Install ([download](https://github.com/mostlygeek/llama-swap/releases)) ## Bare metal Install ([download](https://github.com/mostlygeek/llama-swap/releases))
Pre-built binaries are available for Linux, Mac, Windows and FreeBSD. These are automatically published and are likely a few hours ahead of the docker releases. The baremetal install works with any OpenAI compatible server, not just llama-server. Pre-built binaries are available for Linux, Mac, Windows and FreeBSD. These are automatically published and are likely a few hours ahead of the docker releases. The baremetal install works with any OpenAI compatible server, not just llama-server.
+3
View File
@@ -191,6 +191,9 @@ func (pm *ProxyManager) setupGinEngine() {
pm.ginEngine.GET("/unload", pm.unloadAllModelsHandler) pm.ginEngine.GET("/unload", pm.unloadAllModelsHandler)
pm.ginEngine.GET("/running", pm.listRunningProcessesHandler) pm.ginEngine.GET("/running", pm.listRunningProcessesHandler)
pm.ginEngine.GET("/health", func(c *gin.Context) {
c.String(http.StatusOK, "OK")
})
pm.ginEngine.GET("/favicon.ico", func(c *gin.Context) { pm.ginEngine.GET("/favicon.ico", func(c *gin.Context) {
if data, err := reactStaticFS.ReadFile("ui_dist/favicon.ico"); err == nil { if data, err := reactStaticFS.ReadFile("ui_dist/favicon.ico"); err == nil {
+18
View File
@@ -755,3 +755,21 @@ func TestProxyManager_MiddlewareWritesMetrics_Streaming(t *testing.T) {
assert.Greater(t, lastMetric.TokensPerSecond, 0.0, "tokens per second should be greater than 0") assert.Greater(t, lastMetric.TokensPerSecond, 0.0, "tokens per second should be greater than 0")
assert.Greater(t, lastMetric.DurationMs, 0, "duration should be greater than 0") assert.Greater(t, lastMetric.DurationMs, 0, "duration should be greater than 0")
} }
func TestProxyManager_HealthEndpoint(t *testing.T) {
config := AddDefaultGroupToConfig(Config{
HealthCheckTimeout: 15,
Models: map[string]ModelConfig{
"model1": getTestSimpleResponderConfig("model1"),
},
LogLevel: "error",
})
proxy := New(config)
defer proxy.StopProcesses(StopWaitForInflightRequest)
req := httptest.NewRequest("GET", "/health", nil)
rec := httptest.NewRecorder()
proxy.ServeHTTP(rec, req)
assert.Equal(t, http.StatusOK, rec.Code)
assert.Equal(t, "OK", rec.Body.String())
}