turbollm 1.10.7 → 1.11.0

package/README.md

@@ -222,6 +222,15 @@ the detail:
 - **Saved per-model profiles, per engine** — tune once per (model, engine) pair, so
   switching engines (or between two installs of the same engine, e.g. a fork) never
   overwrites another engine's tuning for the same model.
+- **Named load presets, many per model** — keep "max speed 32k" *and* "200k long context"
+  side by side instead of the second tune overwriting the first. Pick one from the Model
+  Detail panel to fill the load parameters (it's remembered and auto-applied on the next
+  load), **Save as…** captures the current settings, and rename/delete live in the ⋯ menu.
+  **Auto-tune mints a preset every time you save one** — named `Auto-tune <date>` and badged
+  with its measured tok/s — so every tune becomes browsable, restorable history rather than
+  a one-slot overwrite. The ten newest auto-tune presets are kept; your own saves are never
+  pruned. Existing profiles carry over as presets automatically, and a model with no presets
+  behaves exactly as before.
 - **Configurable VRAM headroom** (Settings → Models & loading → Advanced, 300 MB–2 GB, default
   1 GB) — tell auto-tune how much VRAM to keep free for other GPU workloads instead of a fixed margin.
   Drag it to 0 to opt into an experimental **MoE "VRAM-spill" search** — auto-tune keeps pushing more
@@ -468,8 +477,8 @@ switch between CUDA / ROCm / Metal / SYCL / Vulkan / CPU at any time (it downloa
 you choose, LM Studio-style).
 
 **Engine types.** **llama.cpp / GGUF**, **KoboldCpp** and **llamafile** (GGUF, every OS),
-**MLX** (macOS), and **vLLM** (Linux + NVIDIA) are all first-class engine kinds — install from
-the curated catalog, pick the right one per model, and switch from a single dropdown.
+**MLX** and **MLX-VLM** (macOS), and **vLLM** (Linux + NVIDIA) are all first-class engine kinds —
+install from the curated catalog, pick the right one per model, and switch from a single dropdown.
 
 **Fully supervised.** Every engine runs under a real state machine: health-gated readiness,
 graceful stop, an **idle auto-stop** watchdog, and **live logs + clear error surfacing** in

package/dist/{chunk-5MCP2ZAJ.js → chunk-H67DVIQT.js}

@@ -8,16 +8,18 @@ import { join } from "path";
 function engineAcceptsFormat(engineKind, format) {
   if (engineKind === "mlx") return format === "mlx";
   if (engineKind === "rapid-mlx") return format === "mlx";
+  if (engineKind === "mlx-vlm") return format === "mlx";
   if (engineKind === "vllm") return format === "mlx";
   return format === "gguf";
 }
 function engineRejectsAudioModel(engineKind) {
-  return engineKind === "rapid-mlx";
+  return engineKind === "rapid-mlx" || engineKind === "mlx-vlm";
 }
 var ENGINE_MODEL_ALIAS = "default_model";
 var RAPID_MLX_MODEL_ALIAS = "default";
-function engineModelAlias(engineKind) {
+function engineModelAlias(engineKind, modelPath) {
   if (engineKind === "rapid-mlx") return RAPID_MLX_MODEL_ALIAS;
+  if (engineKind === "mlx-vlm") return modelPath ?? null;
   return engineKind === "mlx" || engineKind === "vllm" || engineKind === "sglang" ? ENGINE_MODEL_ALIAS : null;
 }
 var VENDOR_DISPLAY = {
@@ -77,7 +79,7 @@ async function distill(d, material) {
   const ms = d.manager.status();
   const target = d.manager.target();
   if (ms.state !== "running" || !ms.model || !target) return { name: null, description: null, procedure: null };
-  const model = engineModelAlias(d.registry.active()?.kind ?? "") ?? ms.model.key;
+  const model = engineModelAlias(d.registry.active()?.kind ?? "", d.manager.currentOpts()?.modelPath) ?? ms.model.key;
   try {
     const res = await fetch(`${target}/v1/chat/completions`, {
       method: "POST",