ggml-webgpu: Add clang-format job (#24308)

* Add clang-format job

* try local formatting

.github/workflows/build-webgpu.yml

@@ -35,6 +35,29 @@ env:
   LLAMA_ARG_LOG_TIMESTAMPS: 1
 
 jobs:
+  format:
+    runs-on: ubuntu-24.04
+
+    steps:
+      - name: Clone
+        uses: actions/checkout@v6
+
+      - name: Install clang-format 22
+        run: |
+          wget -qO- https://apt.llvm.org/llvm-snapshot.gpg.key |
+            sudo tee /etc/apt/trusted.gpg.d/apt.llvm.org.asc > /dev/null
+          sudo add-apt-repository -y \
+            "deb http://apt.llvm.org/noble/ llvm-toolchain-noble-22 main"
+          sudo apt-get update
+          sudo apt-get install -y clang-format-22
+
+      - name: Check formatting
+        run: |
+          find ggml/src/ggml-webgpu \
+            -type f \( -name '*.cpp' -o -name '*.hpp' -o -name '*.h' \) \
+            -print0 |
+            xargs -0 clang-format-22 --dry-run --Werror
+
   macos:
     runs-on: macos-latest
 

ggml/src/ggml-webgpu/ggml-webgpu-shader-lib.hpp

@@ -644,7 +644,8 @@ inline size_t ggml_webgpu_flash_attn_tensor_offset(const ggml_tensor * tensor) {
 
 inline bool ggml_webgpu_flash_attn_float_vec4_aligned(const ggml_tensor * K, size_t storage_offset_alignment) {
     const uint32_t offset_elems =
-        (uint32_t) ((ggml_webgpu_flash_attn_tensor_offset(K) & (storage_offset_alignment - 1)) / ggml_type_size(K->type));
+        (uint32_t) ((ggml_webgpu_flash_attn_tensor_offset(K) & (storage_offset_alignment - 1)) /
+                    ggml_type_size(K->type));
     return offset_elems % GGML_WEBGPU_FLASH_ATTN_TILE_KV_VEC_WIDTH == 0u;
 }
 
@@ -655,8 +656,10 @@ inline bool ggml_webgpu_flash_attn_float_vec4_aligned(const ggml_tensor * K,
            ggml_webgpu_flash_attn_float_vec4_aligned(V, storage_offset_alignment);
 }
 
-inline bool ggml_webgpu_flash_attn_kv_direct(
+inline bool ggml_webgpu_flash_attn_kv_direct(const ggml_tensor * Q,
-    const ggml_tensor * Q, const ggml_tensor * K, const ggml_tensor * V, uint32_t kv_direct_align) {
+                                             const ggml_tensor * K,
+                                             const ggml_tensor * V,
+                                             uint32_t            kv_direct_align) {
     return K->type == GGML_TYPE_F16 && V->type == GGML_TYPE_F16 && (Q->ne[0] % kv_direct_align == 0) &&
            (K->ne[1] % GGML_WEBGPU_KV_SEQ_PAD == 0);
 }