Commit 9c10c94e1 for llama.cpp

commit 9c10c94e16ebc4f3ed7c06264a93bf7e019c3f26
Author: Alexey Kopytko <alexey@kopytko.com>
Date:   Sun Nov 22 20:10:42 2026 +0900

    ggml : fix nonzero clear on WebGPU and non-UMA devices (#32727)

diff --git a/ggml/src/ggml-vulkan/ggml-vulkan.cpp b/ggml/src/ggml-vulkan/ggml-vulkan.cpp
index efb644793..60cebe494 100644
--- a/ggml/src/ggml-vulkan/ggml-vulkan.cpp
+++ b/ggml/src/ggml-vulkan/ggml-vulkan.cpp
@@ -14279,7 +14279,9 @@ bool ggml_backend_vk_buffer_cpy_tensor_n(ggml_backend_buffer_t buffer, const ggm
 void ggml_backend_vk_buffer_clear(ggml_backend_buffer_t buffer, uint8_t value) {
     ggml_backend_vk_buffer_context * ctx = (ggml_backend_vk_buffer_context *)buffer->context;

-    ggml_vk_buffer_memset(ctx->dev_buffer, 0, value, buffer->size);
+    // set all bytes of a u32 to the same 1 byte value
+    uint32_t val32 = (uint32_t)value * 0x01010101;
+    ggml_vk_buffer_memset(ctx->dev_buffer, 0, val32, buffer->size);
 }

 const char * ggml_backend_vk_buffer_type_name(ggml_backend_buffer_type_t buft) {
diff --git a/ggml/src/ggml-webgpu/ggml-webgpu.cpp b/ggml/src/ggml-webgpu/ggml-webgpu.cpp
index 3fd8a6672..886760849 100644
--- a/ggml/src/ggml-webgpu/ggml-webgpu.cpp
+++ b/ggml/src/ggml-webgpu/ggml-webgpu.cpp
@@ -4066,7 +4066,7 @@ static void ggml_backend_webgpu_buffer_memset_tensor(ggml_backend_buffer_t buffe

     size_t total_offset = ggml_webgpu_tensor_offset(tensor) + offset;

-    // This is a trick to set all bytes of a u32 to the same 1 byte value.
+    // set all bytes of a u32 to the same 1 byte value
     uint32_t val32 = (uint32_t) value * 0x01010101;
     ggml_backend_webgpu_buffer_memset(buf_ctx->global_ctx, buf_ctx->buffer, val32, total_offset, size);
     WEBGPU_CPU_PROFILE_TOTAL_END(memset_tensor, buf_ctx->global_ctx);
@@ -4406,7 +4406,10 @@ static void ggml_backend_webgpu_buffer_clear(ggml_backend_buffer_t buffer, uint8
     WEBGPU_LOG_DEBUG("ggml_backend_webgpu_buffer_clear(" << buffer << ", " << (uint32_t) value << ")");
     WEBGPU_CPU_PROFILE_TOTAL_START(clear);
     ggml_backend_webgpu_buffer_context * buf_ctx = (ggml_backend_webgpu_buffer_context *) buffer->context;
-    ggml_backend_webgpu_buffer_memset(buf_ctx->global_ctx, buf_ctx->buffer, value, 0, buffer->size);
+
+    // set all bytes of a u32 to the same 1 byte value
+    uint32_t val32 = (uint32_t) value * 0x01010101;
+    ggml_backend_webgpu_buffer_memset(buf_ctx->global_ctx, buf_ctx->buffer, val32, 0, buffer->size);
     WEBGPU_CPU_PROFILE_TOTAL_END(clear, buf_ctx->global_ctx);
 }

diff --git a/tests/test-backend-tensor.cpp b/tests/test-backend-tensor.cpp
index 213275f62..84c4dc2bd 100644
--- a/tests/test-backend-tensor.cpp
+++ b/tests/test-backend-tensor.cpp
@@ -223,6 +223,19 @@ static bool test_tensor_n(ggml_backend_buffer_type_t buft) {
         }
     }

+    {
+        uint8_t expected[24], out[24] = {};
+        memset(expected, 0x5A, sizeof(expected));
+
+        // Verify that clear fills every byte with a nonzero value.
+        ggml_backend_buffer_clear(buf.get(), 0x5A);
+
+        ggml_backend_tensor_get(t_big, out, 0, sizeof(out));
+        if (memcmp(out, expected, sizeof(out)) != 0) {
+            return false;
+        }
+    }
+
     return true;
 }