mirror of
https://github.com/mudler/LocalAI.git
synced 2026-04-01 05:36:49 -04:00
6e5a58ca70
* fix: Add VRAM cleanup when stopping models
- Add Free() method to AIModel interface for proper GPU resource cleanup
- Implement Free() in llama backend to release llama.cpp model resources
- Add Free() stub implementations in base and SingleThread backends
- Modify deleteProcess() to call Free() before stopping the process
to ensure VRAM is properly released when models are unloaded
Fixes issue where VRAM was not freed when stopping models, which
could lead to memory exhaustion when running multiple models
sequentially.
* feat: Add Free RPC to backend.proto for VRAM cleanup\n\n- Add rpc Free(HealthMessage) returns (Result) {} to backend.proto\n- This RPC is required to properly expose the Free() method\n through the gRPC interface for VRAM resource cleanup\n\nRefs: PR #8739
* Apply suggestion from @mudler
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
---------
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
Co-authored-by: localai-bot <localai-bot@users.noreply.github.com>
Co-authored-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
40 lines
1.2 KiB
Go
40 lines
1.2 KiB
Go
package grpc
|
|
|
|
import (
|
|
pb "github.com/mudler/LocalAI/pkg/grpc/proto"
|
|
)
|
|
|
|
type AIModel interface {
|
|
Busy() bool
|
|
Lock()
|
|
Unlock()
|
|
Locking() bool
|
|
Predict(*pb.PredictOptions) (string, error)
|
|
PredictStream(*pb.PredictOptions, chan string) error
|
|
Load(*pb.ModelOptions) error
|
|
Free() error
|
|
Embeddings(*pb.PredictOptions) ([]float32, error)
|
|
GenerateImage(*pb.GenerateImageRequest) error
|
|
GenerateVideo(*pb.GenerateVideoRequest) error
|
|
Detect(*pb.DetectOptions) (pb.DetectResponse, error)
|
|
AudioTranscription(*pb.TranscriptRequest) (pb.TranscriptResult, error)
|
|
TTS(*pb.TTSRequest) error
|
|
TTSStream(*pb.TTSRequest, chan []byte) error
|
|
SoundGeneration(*pb.SoundGenerationRequest) error
|
|
TokenizeString(*pb.PredictOptions) (pb.TokenizationResponse, error)
|
|
Status() (pb.StatusResponse, error)
|
|
|
|
StoresSet(*pb.StoresSetOptions) error
|
|
StoresDelete(*pb.StoresDeleteOptions) error
|
|
StoresGet(*pb.StoresGetOptions) (pb.StoresGetResult, error)
|
|
StoresFind(*pb.StoresFindOptions) (pb.StoresFindResult, error)
|
|
|
|
VAD(*pb.VADRequest) (pb.VADResponse, error)
|
|
|
|
ModelMetadata(*pb.ModelOptions) (*pb.ModelMetadataResponse, error)
|
|
}
|
|
|
|
func newReply(s string) *pb.Reply {
|
|
return &pb.Reply{Message: []byte(s)}
|
|
}
|