nikola/llama_cpp
1
0
Fork 0
Code Issues Pull Requests Actions 34 Packages Projects Releases Wiki Activity

ggml webgpu: support for rope,div,sub,glu,scale,cont operators (#16187)

Browse Source 
* Work on rope

* Simplify inplace operation generation and combine mul/add generation

* Work on rope variants

* implement neox rope

* rope complete

* Add sub,div,glu operators

* implement scale op

* Update cpy shader to handle cont/more types

* formatting

* Update test vars printing for rope,rms_norm

* Avoid ROPE hardcoded constants

* Add TODO to change ROPE constants to enum

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* fix TODO comment

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
Reese Levine
2025-09-30 09:57:51 -07:00
committed by GitHub
co-authored by Georgi Gerganov
parent d1c84a662d
commit 8d78cd2613
17 changed files with 1534 additions and 397 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-webgpu/wgsl-shaders/cpy.wgsl
-60
View File
@@ -1,60 +0,0 @@
enable f16;
@group(0) @binding(0)
var<storage, read_write> src: array<f32>;
@group(0) @binding(1)
var<storage, read_write> dst: array<f16>;
struct Params {
ne: u32, // total number of elements
offset_src: u32, // in elements
offset_dst: u32, // in elements
// Strides (in elements) — may be permuted
stride_src0: u32,
stride_src1: u32,
stride_src2: u32,
stride_src3: u32,
stride_dst0: u32,
stride_dst1: u32,
stride_dst2: u32,
stride_dst3: u32,
// Logical shape (same for both tensors)
ne0: u32,
ne1: u32,
ne2: u32,
ne3: u32,
};
@group(0) @binding(2)
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.ne) {
return;
}
var i = gid.x;
let i3 = i / (params.ne2 * params.ne1 * params.ne0);
i = i % (params.ne2 * params.ne1 * params.ne0);
let i2 = i / (params.ne1 * params.ne0);
i = i % (params.ne1 * params.ne0);
let i1 = i / params.ne0;
let i0 = i % params.ne0;
let src_idx = i0 * params.stride_src0 + i1 * params.stride_src1 +
i2 * params.stride_src2 + i3 * params.stride_src3;
let dst_idx = i0 * params.stride_dst0 + i1 * params.stride_dst1 +
i2 * params.stride_dst2 + i3 * params.stride_dst3;
dst[params.offset_dst + dst_idx] = f16(src[params.offset_src + src_idx]);
}