sleepy/llama.cpp
1
0
Fork 0
Code Issues 10 Pull Requests Actions 111 Packages Projects Releases Wiki Activity

Add concat op to webgpu. (#20068)

Browse Source
This commit is contained in:
Masashi Yoshimura
2026-03-05 04:19:00 +09:00
committed by GitHub
parent d969e933e1
commit 541bf37622
5 changed files with 230 additions and 33 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-webgpu/ggml-webgpu.cpp
+67
View File
@@ -1484,6 +1484,68 @@ static webgpu_command ggml_webgpu_binary_op(webgpu_context & ctx,
return ggml_backend_webgpu_build(ctx->global_ctx, ctx->param_buf_pool, pipeline, params, entries, wg_x);
}
static webgpu_command ggml_webgpu_concat(webgpu_context & ctx,
ggml_tensor * src0,
ggml_tensor * src1,
ggml_tensor * dst) {
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 = {
{
.binding = 0,
.buffer = ggml_webgpu_tensor_buf(src0),
.offset = ggml_webgpu_tensor_align_offset(ctx, src0),
.size = ggml_webgpu_tensor_binding_size(ctx, src0)
},
{
.binding = 1,
.buffer = ggml_webgpu_tensor_buf(src1),
.offset = ggml_webgpu_tensor_align_offset(ctx, src1),
.size = ggml_webgpu_tensor_binding_size(ctx, src1)
},
{
.binding = 2,
.buffer = ggml_webgpu_tensor_buf(dst),
.offset = ggml_webgpu_tensor_align_offset(ctx, dst),
.size = ggml_webgpu_tensor_binding_size(ctx, dst)
}
};
ggml_webgpu_shader_lib_context shader_lib_ctx = {
.src0 = src0,
.src1 = src1,
.dst = dst,
.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);
return ggml_backend_webgpu_build(ctx->global_ctx, ctx->param_buf_pool, pipeline, params, entries, wg_x);
}
static webgpu_command ggml_webgpu_rms_norm(webgpu_context & ctx, ggml_tensor * src, ggml_tensor * dst) {
int inplace = ggml_webgpu_tensor_equal(src, dst);
@@ -2068,6 +2130,8 @@ static std::optional<webgpu_command> ggml_webgpu_encode_node(webgpu_context ctx,
case GGML_OP_MUL:
case GGML_OP_DIV:
return ggml_webgpu_binary_op(ctx, src0, src1, node);
case GGML_OP_CONCAT:
return ggml_webgpu_concat(ctx, src0, src1, node);
case GGML_OP_RMS_NORM:
return ggml_webgpu_rms_norm(ctx, src0, node);
case GGML_OP_ROPE:
@@ -2894,6 +2958,9 @@ static bool ggml_backend_webgpu_device_supports_op(ggml_backend_dev_t dev, const
supports_op = (op->type == GGML_TYPE_F32 || op->type == GGML_TYPE_F16) && (src0->type == op->type) &&
(src1->type == op->type);
break;
case GGML_OP_CONCAT:
supports_op = (src0->type == GGML_TYPE_F32 || src0->type == GGML_TYPE_I32);
break;
case GGML_OP_CPY:
case GGML_OP_CONT:
supports_op = ((op->type == GGML_TYPE_F32 || op->type == GGML_TYPE_F16) &&