Commit 8766c0273 for llama.cpp

commit 8766c0273c1f2071028ef4988767ffe38f41a4b2
Author: Gotya-OFFCIAL <zhengfreeman@gmail.com>
Date:   Tue Nov 10 14:08:06 2026 +0800

    sycl: un-gate oneDNN fused SDPA for Alchemist at head_dim=64 (#31574)

    Co-authored-by: Titaniumtown <titaniumtown@proton.me>

diff --git a/ggml/src/ggml-sycl/fattn-onednn.cpp b/ggml/src/ggml-sycl/fattn-onednn.cpp
index 4691c8600..bd7ce8936 100644
--- a/ggml/src/ggml-sycl/fattn-onednn.cpp
+++ b/ggml/src/ggml-sycl/fattn-onednn.cpp
@@ -69,17 +69,6 @@ bool ggml_sycl_flash_attn_ext_onednn_supported(const ggml_tensor * dst, bool use
             }
         }
     }
-    // This is the improved SPDA gate. Rather than gating Alchemist GPUs from all SPDA features, we instead target only the failing shapes.
-    // If the GPU being assessed isn't in the grouping below, it has full access to all SPDA shapes. Otherwise, if it's an Alchemist GPU, we block only the shapes with head sizes that fail.
-    // It is much easier to compare the device to a small list of failing cases than to define all the passing ones.
-    const gpu_arch arch = ggml_sycl_info().devices[ggml_sycl_get_device()].hw_info.arch;
-    bool support_spda = !(arch == gpu_arch::intel_gpu_dg2_g10 ||
-                         arch == gpu_arch::intel_gpu_dg2_g11 ||
-                         arch == gpu_arch::intel_gpu_dg2_g12);
-
-    if (!support_spda && K->ne[0] == 64) {
-        return false;
-    }
     // Optional KV-length ceiling (GGML_SYCL_FA_ONEDNN_MAX_KV, 0 = unlimited). Escape hatch:
     // very long sequences make the fused SDPA slow enough to risk the xe driver watchdog on
     // some stacks; past the cap we fall back to the native FA kernel instead.