Remove mem check

cmd/cmd.go

@@ -800,9 +800,9 @@ func ShowHandler(cmd *cobra.Command, args []string) error {
 		case "parameters":
 			fmt.Println(resp.Parameters)
 		case "system":
-			fmt.Println(resp.System)
+			fmt.Print(resp.System)
 		case "template":
-			fmt.Println(resp.Template)
+			fmt.Print(resp.Template)
 		}
 
 		return nil

llama/runner/runner.go

@@ -161,13 +161,15 @@ func (s *Server) inputs(prompt string, images []ImageData) ([]input, error) {
 
 	for i, part := range parts {
 		// text - tokenize
-		tokens, err := s.lc.Model().Tokenize(part, i == 0, true)
-		if err != nil {
-			return nil, err
-		}
+		if strings.TrimSpace(part) != "" {
+			tokens, err := s.lc.Model().Tokenize(part, i == 0, true)
+			if err != nil {
+				return nil, err
+			}
 
-		for _, t := range tokens {
-			inputs = append(inputs, input{token: t})
+			for _, t := range tokens {
+				inputs = append(inputs, input{token: t})
+			}
 		}
 
 		// image - generate image embedding

llm/server.go

@@ -128,17 +128,6 @@ func NewLlamaServer(gpus discover.GpuInfoList, model string, ggml *GGML, adapter
 		}
 	}
 
-	// On linux and windows, over-allocating CPU memory will almost always result in an error
-	// Darwin has fully dynamic swap so has no direct concept of free swap space
-	if runtime.GOOS != "darwin" {
-		systemMemoryRequired := estimate.TotalSize - estimate.VRAMSize
-		available := systemFreeMemory + systemSwapFreeMemory
-		if systemMemoryRequired > available {
-			slog.Warn("model request too large for system", "requested", format.HumanBytes2(systemMemoryRequired), "available", available, "total", format.HumanBytes2(systemTotalMemory), "free", format.HumanBytes2(systemFreeMemory), "swap", format.HumanBytes2(systemSwapFreeMemory))
-			return nil, fmt.Errorf("model requires more system memory (%s) than is available (%s)", format.HumanBytes2(systemMemoryRequired), format.HumanBytes2(available))
-		}
-	}
-
 	estimate.log()
 
 	// Loop through potential servers