Compare commits

...

4 Commits

Author SHA1 Message Date
Benson Wong 5672cb03fd Update github actions for notifying homebrew build (#212)
Combine homebrew-llama-swap event with the release action
2025-07-30 11:29:03 -07:00
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 68 additions and 3 deletions
+33 -3
View File
@@ -7,6 +7,10 @@ on:
# Allows manual triggering of the workflow
workflow_dispatch:
inputs:
tag:
description: 'Tag version to release (e.g. v144)'
required: true
permissions:
contents: write
@@ -20,15 +24,15 @@ jobs:
uses: actions/checkout@v4
with:
fetch-depth: 0
ref: ${{ github.event.inputs.tag || github.ref }}
-
name: Set up Go
uses: actions/setup-go@v5
-
name: Set up Node.js
uses: actions/setup-node@v4
with:
node-version: '23' # or your preferred version
node-version: '23'
-
name: Install dependencies and build UI
run: |
@@ -46,4 +50,30 @@ jobs:
version: '~> v2'
args: release --clean
env:
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
trigger-tap-update:
runs-on: ubuntu-latest
needs: goreleaser
steps:
- name: "Resolve tag to dispatch"
id: tag
run: |
if [[ "${{ github.event_name }}" == "workflow_dispatch" ]]; then
echo "tag=${{ github.event.inputs.tag }}" >> "$GITHUB_OUTPUT"
else
echo "tag=${{ github.ref_name }}" >> "$GITHUB_OUTPUT"
fi
- name: "Trigger tap repository update"
uses: peter-evans/repository-dispatch@v2
with:
token: ${{ secrets.TAP_REPO_PAT }}
repository: mostlygeek/homebrew-llama-swap
event-type: new-release
client-payload: |
{
"release": {
"tag_name": "${{ steps.tag.outputs.tag }}"
}
}
+14
View File
@@ -122,6 +122,20 @@ $ docker run -it --rm --runtime nvidia -p 9292:8080 \
</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))
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("/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) {
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.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())
}