vulkan: Convert FILL to distribute workgroups in 2D to avoid exceeding maxComputeWorkGroupCount (#28592)

* divide workload to 2D

This is to workaround FILL exceeding maxComputeWorkGroupCount for Intel GPUs on Qwen 3.8 flash next

* minor change

* Fixed comment

ggml/src/ggml-vulkan/ggml-vulkan.cpp

@@ -13748,9 +13748,11 @@ static void ggml_vk_arange(ggml_backend_vk_context * ctx, vk_context& subctx, gg
 
 static void ggml_vk_fill(ggml_backend_vk_context * ctx, vk_context& subctx, ggml_tensor * dst) {
     VK_LOG_DEBUG("ggml_vk_fill(dst=" << dst << ", ne=" << ggml_nelements(dst) << ")");
+    const uint64_t n = ggml_nelements(dst);
+    GGML_ASSERT(n > 0);
 
     vk_op_push_constants pc = {
-        (uint32_t)ggml_nelements(dst),
+        (uint32_t)n,
         1,
         ggml_get_op_params_f32(dst, 0),
         0.0f,
@@ -13760,11 +13762,16 @@ static void ggml_vk_fill(ggml_backend_vk_context * ctx, vk_context& subctx, ggml
     vk_pipeline pipeline = ggml_vk_op_get_pipeline(ctx, nullptr, nullptr, nullptr, dst, GGML_OP_FILL);
     GGML_ASSERT(pipeline != nullptr);
 
+    // Split the task distribution to 2D to avoid exceeding maxComputeWorkGroupCount
+    const uint32_t total_wg = CEIL_DIV(n, pipeline->wg_denoms[0]);
+    const uint32_t wg_x = std::min(total_wg, ctx->device->properties.limits.maxComputeWorkGroupCount[0]);
+    const uint32_t wg_y = CEIL_DIV(total_wg, wg_x);
+    GGML_ASSERT(wg_y <= ctx->device->properties.limits.maxComputeWorkGroupCount[1]);
+
     ggml_pipeline_request_descriptor_sets(ctx, pipeline, 1);
     vk_subbuffer dst_buf = ggml_vk_tensor_subbuffer(ctx, dst, false);
 
-    std::array<uint32_t, 3> elements = { (uint32_t)ggml_nelements(dst), 1, 1 };
-
+    std::array<uint32_t, 3> elements = { wg_x * pipeline->wg_denoms[0], wg_y * pipeline->wg_denoms[1], 1 };
     ggml_vk_dispatch_pipeline(ctx, subctx, pipeline, { dst_buf }, pc, elements);
 }
 

ggml/src/ggml-vulkan/vulkan-shaders/fill.comp

@@ -8,7 +8,9 @@ layout(local_size_x = 512, local_size_y = 1, local_size_z = 1) in;
 layout (binding = 0) writeonly buffer D {D_TYPE data_d[];};
 
 void main() {
-    const uint i = gl_GlobalInvocationID.x;
+    // 2D grid flattening: each x workgroup covers gl_WorkGroupSize.x elements,
+    // each y workgroup covers gl_NumWorkGroups.x * gl_WorkGroupSize.x elements.
+    const uint i = (gl_GlobalInvocationID.y * gl_NumWorkGroups.x * gl_WorkGroupSize.x) + gl_GlobalInvocationID.x;
 
     if (i >= p.KX) {
         return;

gguf-py/pyproject.toml

@@ -7,7 +7,7 @@ dynamic = ["classifiers"]
 readme = "README.md"
 authors = [{name = "GGML", email = "ggml@ggml.ai"}]
 requires-python = '>=3.10'
-dependencies = ['numpy (>=1.17)', 'tqdm (>=4.27)', 'pyyaml (>=5.1)', 'requests (>=2.25)']
+dependencies = ['numpy (>=2.2.6)', 'tqdm (>=4.27)', 'pyyaml (>=5.1)', 'requests (>=2.25)']
 classifiers = [
     "Programming Language :: Python :: 3",
     "License :: OSI Approved :: MIT License",

pyproject.toml

@@ -8,7 +8,7 @@ readme = "README.md"
 authors = [{name = "GGML", email = "ggml@ggml.ai"}]
 requires-python = '>=3.10,<3.15'
 dependencies = [
-    'numpy (>=1.26.4,<3.0.0)',
+    'numpy (>=2.2.6,<3.0.0)',
     'sentencepiece (>=0.1.98,<0.3.0)',
     'transformers (==4.57.6)',
     'protobuf (>=4.21.0,<5.0.0)',

requirements/requirements-convert_legacy_llama.txt

@@ -1,4 +1,4 @@
-numpy~=1.26.4
+numpy~=2.2.6
 sentencepiece>=0.1.98,<0.3.0
 
 transformers==4.57.6

requirements/requirements-gguf_editor_gui.txt

@@ -1,3 +1,3 @@
-numpy~=1.26.4
+numpy~=2.2.6
 PySide6~=6.9.0
 gguf>=0.17.0

requirements/requirements-server-bench.txt

@@ -1,5 +1,5 @@
 datasets~=4.8.0
 matplotlib~=3.10.0
-numpy~=1.26.4
+numpy~=2.2.6
 requests~=2.32.3
 tqdm~=4.67.1

requirements/requirements-tool_bench.txt

@@ -1,7 +1,7 @@
 aiohttp~=3.9.3
 pytest~=8.3.3
 matplotlib~=3.10.0
-numpy~=1.26.4
+numpy~=2.2.6
 openai~=2.14.0
 pandas~=2.2.3
 prometheus-client~=0.20.0

tools/server/tests/requirements.txt

@@ -2,7 +2,7 @@ aiohttp~=3.9.3
 pytest~=8.3.3
 pytest-xdist~=3.6
 filelock~=3.16
-numpy~=1.26.4
+numpy~=2.2.6
 openai~=2.14.0
 prometheus-client~=0.20.0
 requests~=2.32.3