Lumpiasty/llama.cpp
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

[ggml-webgpu] Handle buffer overlap / buffer aliasing for concat operator (#24000)

Browse Source 
* Only run webgpu CI on my fork

* Add webgpu only workflow

* handle buffer overlap case for concat operator

* restore build-webgpu.yml

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* Run clang-format

* Update ggml/src/ggml-webgpu/wgsl-shaders/concat.wgsl

---------

Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
Co-authored-by: Reese Levine <reeselevine1@gmail.com>
This commit is contained in:
Nikhil Jain
2026-06-08 08:07:31 -07:00
committed by GitHub
co-authored by Claude Sonnet 4.6 Reese Levine
parent 3b3da01dc2
commit 1705d434f6
3 changed files with 79 additions and 33 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-webgpu/ggml-webgpu.cpp
+46 -29
View File
@@ -2310,33 +2310,6 @@ static webgpu_encoded_op ggml_webgpu_concat(webgpu_context & ctx,
uint32_t ne = (uint32_t) ggml_nelements(dst);
uint32_t dim = (uint32_t) dst->op_params[0];
std::vector<uint32_t> params = {
ne,
(uint32_t) (ggml_webgpu_tensor_misalignment(ctx, src0) / ggml_type_size(src0->type)),
(uint32_t) (ggml_webgpu_tensor_misalignment(ctx, src1) / ggml_type_size(src1->type)),
(uint32_t) (ggml_webgpu_tensor_misalignment(ctx, dst) / ggml_type_size(dst->type)),
(uint32_t) (src0->nb[0] / ggml_type_size(src0->type)),
(uint32_t) (src0->nb[1] / ggml_type_size(src0->type)),
(uint32_t) (src0->nb[2] / ggml_type_size(src0->type)),
(uint32_t) (src0->nb[3] / ggml_type_size(src0->type)),
(uint32_t) (src1->nb[0] / ggml_type_size(src1->type)),
(uint32_t) (src1->nb[1] / ggml_type_size(src1->type)),
(uint32_t) (src1->nb[2] / ggml_type_size(src1->type)),
(uint32_t) (src1->nb[3] / ggml_type_size(src1->type)),
(uint32_t) dst->ne[0],
(uint32_t) dst->ne[1],
(uint32_t) dst->ne[2],
(uint32_t) dst->ne[3],
dim,
(uint32_t) src0->ne[dim]
};
std::vector<wgpu::BindGroupEntry> entries = {
ggml_webgpu_make_tensor_bind_group_entry(ctx, 0, src0),
ggml_webgpu_make_tensor_bind_group_entry(ctx, 1, src1),
ggml_webgpu_make_tensor_bind_group_entry(ctx, 2, dst),
};
ggml_webgpu_shader_lib_context shader_lib_ctx = {};
shader_lib_ctx.src0 = src0;
shader_lib_ctx.src1 = src1;
@@ -2344,8 +2317,52 @@ static webgpu_encoded_op ggml_webgpu_concat(webgpu_context & ctx,
shader_lib_ctx.max_wg_size = ctx->global_ctx->capabilities.limits.maxComputeInvocationsPerWorkgroup;
webgpu_pipeline pipeline = ctx->shader_lib->get_concat_pipeline(shader_lib_ctx);
auto * decisions = static_cast<ggml_webgpu_generic_shader_decisions *>(pipeline.context.get());
uint32_t wg_x = CEIL_DIV(ne, decisions->wg_size);
auto * decisions = static_cast<ggml_webgpu_binary_shader_decisions *>(pipeline.context.get());
uint32_t offset_src0 = (uint32_t) (ggml_webgpu_tensor_misalignment(ctx, src0) / ggml_type_size(src0->type));
uint32_t offset_src1 = (uint32_t) (ggml_webgpu_tensor_misalignment(ctx, src1) / ggml_type_size(src1->type));
size_t merged_offset = 0;
size_t merged_size = 0;
if (decisions->src_overlap) {
const ggml_webgpu_merged_binding_range merged_range =
ggml_webgpu_tensor_merged_binding_range(ctx, { src0, src1 });
merged_offset = merged_range.offset;
merged_size = merged_range.size;
offset_src0 = ggml_webgpu_tensor_merged_element_offset(src0, merged_range);
offset_src1 = ggml_webgpu_tensor_merged_element_offset(src1, merged_range);
}
std::vector<uint32_t> params = { ne,
offset_src0,
offset_src1,
(uint32_t) (ggml_webgpu_tensor_misalignment(ctx, dst) / ggml_type_size(dst->type)),
(uint32_t) (src0->nb[0] / ggml_type_size(src0->type)),
(uint32_t) (src0->nb[1] / ggml_type_size(src0->type)),
(uint32_t) (src0->nb[2] / ggml_type_size(src0->type)),
(uint32_t) (src0->nb[3] / ggml_type_size(src0->type)),
(uint32_t) (src1->nb[0] / ggml_type_size(src1->type)),
(uint32_t) (src1->nb[1] / ggml_type_size(src1->type)),
(uint32_t) (src1->nb[2] / ggml_type_size(src1->type)),
(uint32_t) (src1->nb[3] / ggml_type_size(src1->type)),
(uint32_t) dst->ne[0],
(uint32_t) dst->ne[1],
(uint32_t) dst->ne[2],
(uint32_t) dst->ne[3],
dim,
(uint32_t) src0->ne[dim] };
std::vector<wgpu::BindGroupEntry> entries = {};
if (decisions->src_overlap) {
entries.push_back(
ggml_webgpu_make_bind_group_entry(0, ggml_webgpu_tensor_buf(src0), merged_offset, merged_size));
entries.push_back(ggml_webgpu_make_tensor_bind_group_entry(ctx, 1, dst));
} else {
entries.push_back(ggml_webgpu_make_tensor_bind_group_entry(ctx, 0, src0));
entries.push_back(ggml_webgpu_make_tensor_bind_group_entry(ctx, 1, src1));
entries.push_back(ggml_webgpu_make_tensor_bind_group_entry(ctx, 2, dst));
}
uint32_t wg_x = CEIL_DIV(ne, decisions->wg_size);
return ggml_backend_webgpu_build(ctx, pipeline, params, entries, wg_x);
}