Files
llama.cpp-mtp-turboquant/ggml/src/ggml-webgpu/wgsl-shaders/scale.wgsl
T
Reese Levine 238856ec8f ggml webgpu: shader library organization (#19530)
* Basic JIT compilation for mul_mat, get_rows, and scale (#17)

* scale jit working

* preliminary working jit for getrows and mulmat, needs refining

* simplified mul_mat preprocessing switch statement

* get_rows fixes, mul_mat refinement

* formatted + last edits

* removed some extraneous prints

* fixed get_rows, fixed workgroup dispatch in mul_mat. no gibberish

* small fix

* some changes, working

* get_rows and mul_mat jit fixed and working

* Update formatting

* formatting

* Add header

---------

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

* Start work on all-encompassing shader library

* refactor argmax, set_rows

* Refactor all but flashattention, mat mul

* flashattention and matrix multiplication moved to new format

* clean up preprocessing

* Formatting

* remove duplicate constants

* Split large shaders into multiple static strings

---------

Co-authored-by: neha-ha <137219201+neha-ha@users.noreply.github.com>
2026-02-18 07:51:02 -07:00

64 lines
1.4 KiB
WebGPU Shading Language

#ifdef INPLACE
@group(0) @binding(1)
var<uniform> params: Params;
fn store_scale(val: f32, offset: u32) {
src[offset] = val;
}
#else
@group(0) @binding(1)
var<storage, read_write> dst: array<f32>;
@group(0) @binding(2)
var<uniform> params: Params;
fn store_scale(val: f32, offset: u32) {
dst[offset] = val;
}
#endif
struct Params {
offset_src: u32,
offset_dst: u32,
// Strides (in elements)
stride_src1: u32,
stride_src2: u32,
stride_src3: u32,
stride_dst1: u32,
stride_dst2: u32,
stride_dst3: u32,
ne: u32,
ne0: u32,
ne1: u32,
ne2: u32,
scale: f32,
bias: f32
};
@group(0) @binding(0)
var<storage, read_write> src: array<f32>;
@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 i_src = params.offset_src + i3 * params.stride_src3 + i2 * params.stride_src2 + i1 * params.stride_src1 + i0;
let i_dst = params.offset_dst + i3 * params.stride_dst3 + i2 * params.stride_dst2 + i1 * params.stride_dst1 + i0;
store_scale(src[i_src] * params.scale + params.bias, i_dst);
}