chore(cli): be consistent between workers and expose ExtraLLamaCPPArg…

…s to both

Signed-off-by: Ettore Di Giacinto <[email protected]>

core/cli/worker/worker.go

@@ -2,6 +2,7 @@ package worker
 
 type WorkerFlags struct {
 	BackendAssetsPath string `env:"LOCALAI_BACKEND_ASSETS_PATH,BACKEND_ASSETS_PATH" type:"path" default:"/tmp/localai/backend_data" help:"Path used to extract libraries that are required by some of the backends in runtime" group:"storage"`
+	ExtraLLamaCPPArgs string `name:"llama-cpp-args" env:"LOCALAI_EXTRA_LLAMA_CPP_ARGS,EXTRA_LLAMA_CPP_ARGS" help:"Extra arguments to pass to llama-cpp-rpc-server"`
 }
 
 type Worker struct {

core/cli/worker/worker_llamacpp.go

@@ -3,6 +3,7 @@ package worker
 import (
 	"fmt"
 	"os"
+	"strings"
 	"syscall"
 
 	cliContext "github.com/mudler/LocalAI/core/cli/context"
@@ -36,8 +37,9 @@ func (r *LLamaCPP) Run(ctx *cliContext.Context) error {
 
 	args := os.Args[4:]
 	args, grpcProcess = library.LoadLDSO(r.BackendAssetsPath, args, grpcProcess)
-
 	args = append([]string{grpcProcess}, args...)
+	extraArgs := strings.Split(r.ExtraLLamaCPPArgs, " ")
+	args = append(args, extraArgs...)
 	return syscall.Exec(
 		grpcProcess,
 		args,

core/cli/worker/worker_p2p.go

@@ -25,7 +25,6 @@ type P2P struct {
 	NoRunner           bool   `env:"LOCALAI_NO_RUNNER,NO_RUNNER" help:"Do not start the llama-cpp-rpc-server"`
 	RunnerAddress      string `env:"LOCALAI_RUNNER_ADDRESS,RUNNER_ADDRESS" help:"Address of the llama-cpp-rpc-server"`
 	RunnerPort         string `env:"LOCALAI_RUNNER_PORT,RUNNER_PORT" help:"Port of the llama-cpp-rpc-server"`
-	ExtraLLamaCPPArgs  string `name:"llama-cpp-args" env:"LOCALAI_EXTRA_LLAMA_CPP_ARGS,EXTRA_LLAMA_CPP_ARGS" help:"Extra arguments to pass to llama-cpp-rpc-server"`
 	Peer2PeerNetworkID string `env:"LOCALAI_P2P_NETWORK_ID,P2P_NETWORK_ID" help:"Network ID for P2P mode, can be set arbitrarly by the user for grouping a set of instances" group:"p2p"`
 }