Files
LocalAI/core/http/routes/quantization.go
Ettore Di Giacinto 59108fbe32 feat: add distributed mode (#9124)
* feat: add distributed mode (experimental)

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* fix data races, mutexes, transactions

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* refactorings

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* fixups

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* fix events and tool stream in agent chat

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* use ginkgo

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* refactoring and consolidation

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* refactoring and consolidation

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* refactoring and consolidation

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* refactoring and consolidation

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* refactoring and consolidation

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* refactoring and consolidation

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* refactoring and consolidation

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* refactoring and consolidation

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* fix(cron): compute correctly time boundaries avoiding re-triggering

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* enhancements, refactorings

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* do not flood of healthy checks

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* do not list obvious backends as text backends

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* tests fixups

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* refactoring and consolidation

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Drop redundant healthcheck

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* enhancements, refactorings

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2026-03-30 00:47:27 +02:00

41 lines
1.5 KiB
Go

package routes
import (
"net/http"
"github.com/labstack/echo/v4"
"github.com/mudler/LocalAI/core/config"
"github.com/mudler/LocalAI/core/http/endpoints/localai"
"github.com/mudler/LocalAI/core/services/quantization"
)
// RegisterQuantizationRoutes registers quantization API routes.
func RegisterQuantizationRoutes(e *echo.Echo, qService *quantization.QuantizationService, appConfig *config.ApplicationConfig, quantizationMw echo.MiddlewareFunc) {
if qService == nil {
return
}
// Service readiness middleware
readyMw := func(next echo.HandlerFunc) echo.HandlerFunc {
return func(c echo.Context) error {
if qService == nil {
return c.JSON(http.StatusServiceUnavailable, map[string]string{
"error": "quantization service is not available",
})
}
return next(c)
}
}
q := e.Group("/api/quantization", readyMw, quantizationMw)
q.GET("/backends", localai.ListQuantizationBackendsEndpoint(appConfig))
q.POST("/jobs", localai.StartQuantizationJobEndpoint(qService))
q.GET("/jobs", localai.ListQuantizationJobsEndpoint(qService))
q.GET("/jobs/:id", localai.GetQuantizationJobEndpoint(qService))
q.POST("/jobs/:id/stop", localai.StopQuantizationJobEndpoint(qService))
q.DELETE("/jobs/:id", localai.DeleteQuantizationJobEndpoint(qService))
q.GET("/jobs/:id/progress", localai.QuantizationProgressEndpoint(qService))
q.POST("/jobs/:id/import", localai.ImportQuantizedModelEndpoint(qService))
q.GET("/jobs/:id/download", localai.DownloadQuantizedModelEndpoint(qService))
}