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

ggml webgpu: minor set rows optimization (#16810)

Browse Source 
* Add buffer label and enable dawn-specific toggles to turn off some checks

* Minor set_rows optimization (#4)

* updated optimization, fixed errors

* non vectorized version now dispatches one thread per element

* Simplify

* Change logic for set_rows pipelines

---------

Co-authored-by: Neha Abbas <nehaabbas@macbookpro.lan>
Co-authored-by: Neha Abbas <nehaabbas@ReeseLevines-MacBook-Pro.local>
Co-authored-by: Reese Levine <reeselevine1@gmail.com>

* Comment on dawn toggles

* Remove some comments

* Implement overlap binary operators

* Revert "Implement overlap binary operators"

This reverts commit ed710b36f51ab3f53fa13db15c1685dc8678a32a.

* Disable support for non-contiguous binary_op tensors and leave note for future support

---------

Co-authored-by: neha-ha <137219201+neha-ha@users.noreply.github.com>
Co-authored-by: Neha Abbas <nehaabbas@macbookpro.lan>
Co-authored-by: Neha Abbas <nehaabbas@ReeseLevines-MacBook-Pro.local>
This commit is contained in:
Reese Levine
2025-11-05 10:27:42 +01:00
committed by GitHub
co-authored by Neha Abbas Neha Abbas neha-ha
parent cdabeb2c27
commit 03ea04175d
2 changed files with 103 additions and 30 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-webgpu/wgsl-shaders/set_rows.wgsl → ggml/src/ggml-webgpu/wgsl-shaders/set_rows.tmpl.wgsl
+38 -7
View File
@@ -1,13 +1,38 @@
#define(VARIANTS)
[
{
"SHADER_SUFFIX": "f16_vec",
"REPLS": {
"TYPE" : "vec4<f32>",
"DST_TYPE": "vec4<f16>",
"VEC_SIZE": 4
}
},
{
"SHADER_SUFFIX": "f16",
"REPLS": {
"TYPE" : "f32",
"DST_TYPE": "f16",
"VEC_SIZE": 1
}
}
]
#end(VARIANTS)
#define(SHADER)
enable f16;
@group(0) @binding(0)
var<storage, read_write> src: array<f32>;
var<storage, read_write> src: array<{{TYPE}}>;
@group(0) @binding(1)
var<storage, read_write> idx: array<u32>;
@group(0) @binding(2)
var<storage, read_write> dst: array<f16>;
var<storage, read_write> dst: array<{{DST_TYPE}}>;
@group(0) @binding(3)
var<storage, read_write> error: atomic<u32>;
@@ -47,10 +72,14 @@ var<uniform> params: Params;
override wg_size: u32;
@compute @workgroup_size(wg_size)
fn main(@builtin(global_invocation_id) gid: vec3<u32>) {
if (gid.x >= params.n_rows * params.ne2 * params.ne3) {
if (gid.x >= (params.ne3 * params.ne2 * params.n_rows * params.ne0) / {{VEC_SIZE}}) {
return;
}
var i = gid.x;
// getting the row from gid
let elems_per_row = params.ne0 / {{VEC_SIZE}};
var i = gid.x / elems_per_row;
let i_src3 = i / (params.ne2 * params.n_rows);
i = i % (params.ne2 * params.n_rows);
@@ -75,7 +104,9 @@ fn main(@builtin(global_invocation_id) gid: vec3<u32>) {
let i_dst_row = params.offset_dst + idx_high_val * params.stride_dst1 + i_src2 * params.stride_dst2 + i_src3 * params.stride_dst3;
let i_src_row = params.offset_src + i_src1 * params.stride_src1 + i_src2 * params.stride_src2 + i_src3 * params.stride_src3;
for (var i: u32 = 0; i < params.ne0; i++) {
dst[i_dst_row + i] = f16(src[i_src_row + i]);
}
let col_idx = (gid.x % elems_per_row);
dst[i_dst_row/{{VEC_SIZE}} + col_idx] = {{DST_TYPE}}(src[i_src_row/{{VEC_SIZE}} + col_idx]);
}
#end(SHADER)