[ggml-webgpu] Handle buffer overlap / buffer aliasing for concat operator (#24000)
* 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:
co-authored by
Claude Sonnet 4.6
Reese Levine
parent
3b3da01dc2
commit
1705d434f6
@@ -31,6 +31,16 @@ struct Params {
|
||||
#define DataType i32
|
||||
#endif
|
||||
|
||||
#ifdef SRC_OVERLAP
|
||||
@group(0) @binding(0)
|
||||
var<storage, read_write> merged_src: array<DataType>;
|
||||
|
||||
@group(0) @binding(1)
|
||||
var<storage, read_write> dst: array<DataType>;
|
||||
|
||||
@group(0) @binding(2)
|
||||
var<uniform> params: Params;
|
||||
#else
|
||||
@group(0) @binding(0)
|
||||
var<storage, read_write> src0: array<DataType>;
|
||||
|
||||
@@ -42,7 +52,7 @@ var<storage, read_write> dst: array<DataType>;
|
||||
|
||||
@group(0) @binding(3)
|
||||
var<uniform> params: Params;
|
||||
|
||||
#endif
|
||||
@compute @workgroup_size(WG_SIZE)
|
||||
fn main(@builtin(global_invocation_id) gid: vec3<u32>) {
|
||||
|
||||
@@ -62,14 +72,22 @@ fn main(@builtin(global_invocation_id) gid: vec3<u32>) {
|
||||
ni[1] * params.stride_src0_1 +
|
||||
ni[2] * params.stride_src0_2 +
|
||||
ni[3] * params.stride_src0_3;
|
||||
#ifdef SRC_OVERLAP
|
||||
dst[params.offset_dst + gid.x] = merged_src[params.offset_src0 + src_i];
|
||||
#else
|
||||
dst[params.offset_dst + gid.x] = src0[params.offset_src0 + src_i];
|
||||
#endif
|
||||
} else {
|
||||
ni[params.dim] -= params.src0_nedim;
|
||||
let src_i = ni[0] * params.stride_src1_0 +
|
||||
ni[1] * params.stride_src1_1 +
|
||||
ni[2] * params.stride_src1_2 +
|
||||
ni[3] * params.stride_src1_3;
|
||||
#ifdef SRC_OVERLAP
|
||||
dst[params.offset_dst + gid.x] = merged_src[params.offset_src1 + src_i];
|
||||
#else
|
||||
dst[params.offset_dst + gid.x] = src1[params.offset_src1 + src_i];
|
||||
#endif
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user