Optimize Qwen3.8 inference on Apple silicon

src/engine/metal/gpu.rs

@@ -8,6 +8,7 @@ pub(super) struct GpuTensor {
 #[derive(Clone, Copy)]
 #[repr(C)]
 pub(super) struct QwenWeightView {
+    pub(super) tensor: *const GpuTensor,
     pub(super) map: *const c_void,
     pub(super) size: u64,
     pub(super) offset: u64,
@@ -90,6 +91,7 @@ pub(super) struct StreamExpertCacheStats {
 unsafe extern "C" {
     pub(super) fn ds4_gpu_init() -> i32;
     pub(super) fn ds4_gpu_cleanup();
+    pub(super) fn ds4_gpu_metal4_tensor_api_enabled() -> i32;
     pub(super) fn ds4_gpu_set_model_map_range(
         model_map: *const c_void,
         model_size: u64,
@@ -103,6 +105,7 @@ unsafe extern "C" {
         a: *const GpuTensor,
         b: *const GpuTensor,
         c: *const GpuTensor,
+        d: *const GpuTensor,
         weights: *const QwenWeightView,
         weight_count: u32,
         args: *const QwenKernelArgs,
@@ -132,6 +135,7 @@ unsafe extern "C" {
     ) -> i32;
     pub(super) fn ds4_gpu_set_quality(quality: bool);
     pub(super) fn ds4_gpu_set_glm_model(enabled: bool);
+    pub(super) fn ds4_gpu_set_qwen_model(enabled: bool);
     pub(super) fn ds4_gpu_set_ssd_streaming(enabled: bool);
     pub(super) fn ds4_gpu_set_model_fd(fd: i32) -> i32;
     pub(super) fn ds4_gpu_set_streaming_expert_cache_budget(experts: u32);
@@ -199,6 +203,7 @@ unsafe extern "C" {
     pub(super) fn ds4_gpu_parallel_ffn_finish() -> i32;
     pub(super) fn ds4_gpu_parallel_ffn_abort();
     pub(super) fn ds4_gpu_tensor_alloc(bytes: u64) -> *mut GpuTensor;
+    pub(super) fn ds4_gpu_tensor_alloc_untracked(bytes: u64) -> *mut GpuTensor;
     pub(super) fn ds4_gpu_tensor_view(
         base: *const GpuTensor,
         offset: u64,
@@ -1847,6 +1852,7 @@ impl Context {
         check(unsafe { ds4_gpu_init() }, "Metal initialization")?;
         unsafe {
             ds4_gpu_set_glm_model(model.shape.family == ModelFamily::Glm);
+            ds4_gpu_set_qwen_model(false);
             ds4_gpu_set_ssd_streaming(ssd_streaming);
             // Decode enables this only around DS4's eligible resident pre-M5
             // MXFP4 token path; all other work starts from the portable path.
@@ -1944,6 +1950,7 @@ impl Context {
         check(unsafe { ds4_gpu_init() }, "Metal initialization")?;
         unsafe {
             ds4_gpu_set_glm_model(false);
+            ds4_gpu_set_qwen_model(true);
             ds4_gpu_set_ssd_streaming(false);
             ds4_gpu_set_decode_pipeline_fast_lookup(0);
         }
@@ -2071,6 +2078,12 @@ impl Buffer {
             .ok_or_else(|| format!("Metal could not allocate {bytes} bytes"))
     }
 
+    pub(super) fn untracked(bytes: u64) -> Result<Self, String> {
+        NonNull::new(unsafe { ds4_gpu_tensor_alloc_untracked(bytes) })
+            .map(Self)
+            .ok_or_else(|| format!("Metal could not allocate {bytes} untracked bytes"))
+    }
+
     pub(super) fn view(&self, offset: u64, bytes: u64) -> Result<Self, String> {
         // SAFETY: `ds4_gpu_tensor_view` in native/metal/ds4_metal.m bounds-checks
         // the view, ARC-retains base_obj.buffer, and marks the view non-owning, so