refactor error

llm/server.go

@@ -82,7 +82,7 @@ func LoadModel(model string, maxArraySize int) (*GGML, error) {
 
 // NewLlamaServer will run a server for the given GPUs
 // The gpu list must be a single family.
-func NewLlamaServer(gpus gpu.GpuInfoList, model string, ggml *GGML, adapters, projectors []string, opts api.Options) (LlamaServer, error) {
+func NewLlamaServer(gpus gpu.GpuInfoList, model string, ggml *GGML, adapters, projectors []string, opts api.Options, numParallel int) (LlamaServer, error) {
 	var err error
 	var cpuRunner string
 	var estimate MemoryEstimate
@@ -218,8 +218,10 @@ func NewLlamaServer(gpus gpu.GpuInfoList, model string, ggml *GGML, adapters, pr
 
 	// Windows CUDA should not use mmap for best performance
 	// Linux  with a model larger than free space, mmap leads to thrashing
+	// For CPU loads we want the memory to be allocated, not FS cache
 	if (runtime.GOOS == "windows" && gpus[0].Library == "cuda" && opts.UseMMap == api.TriStateUndefined) ||
 		(runtime.GOOS == "linux" && systemFreeMemory < estimate.TotalSize && opts.UseMMap == api.TriStateUndefined) ||
+		(gpus[0].Library == "cpu" && opts.UseMMap == api.TriStateUndefined) ||
 		opts.UseMMap == api.TriStateFalse {
 		params = append(params, "--no-mmap")
 	}
@@ -232,15 +234,6 @@ func NewLlamaServer(gpus gpu.GpuInfoList, model string, ggml *GGML, adapters, pr
 		params = append(params, "--numa")
 	}
 
-	numParallel := envconfig.NumParallel
-
-	// TODO (jmorganca): multimodal models don't support parallel yet
-	// see https://github.com/ollama/ollama/issues/4165
-	if len(projectors) > 0 {
-		numParallel = 1
-		slog.Warn("multimodal models don't support parallel requests yet")
-	}
-
 	params = append(params, "--parallel", fmt.Sprintf("%d", numParallel))
 
 	if estimate.TensorSplit != "" {
@@ -567,6 +560,9 @@ func (s *llmServer) WaitUntilRunning(ctx context.Context) error {
 			if s.status != nil && s.status.LastErrMsg != "" {
 				msg = s.status.LastErrMsg
 			}
+			if strings.Contains(msg, "unknown model") {
+				return fmt.Errorf("this model is not supported by your version of Ollama. You may need to upgrade.")
+			}
 			return fmt.Errorf("llama runner process has terminated: %v %s", err, msg)
 		default:
 		}

llm/status.go

@@ -25,6 +25,7 @@ var errorPrefixes = []string{
 	"CUDA error",
 	"cudaMalloc failed",
 	"\"ERR\"",
+	"architecture",
 }
 
 func (w *StatusWriter) Write(b []byte) (int, error) {
@@ -34,19 +35,6 @@ func (w *StatusWriter) Write(b []byte) (int, error) {
 			errMsg = prefix + string(bytes.TrimSpace(after))
 		}
 	}
-
-	if bytes.Contains(b, []byte("unknown model architecture")) {
-		if _, after, ok := bytes.Cut(b, []byte("architecture")); ok {
-			errMsg = "error" + string(bytes.TrimSpace(after))
-
-			if before, _, ok := bytes.Cut(after, []byte("llama_load")); ok {
-				errMsg = "error" + string(bytes.TrimSpace(before))
-			}
-
-			errMsg = errMsg + "\nYour current version of Ollama doesn't support this model architecture. Consider upgrading."
-		}
-	}
-
 	if errMsg != "" {
 		w.LastErrMsg = errMsg
 	}