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

ggml webgpu: profiling, CI updates, reworking of command submission (#16452)

Browse Source 
* Add profiling

* More detailed profiling

* Rework command submission to avoid global locks

* Update wait handling

* try new method of waiting on futures

* Add serializing of command submission in some cases

* Add new pool for timestamp queries and clean up logging

* Serialize command submission in CI and leave a TODO note

* Update webgpu CI

* Add myself as WebGPU codeowner

* Deadlock avoidance

* Leave WebGPU/Vulkan CI serialized

* Fix divide by 0

* Fix logic in division by inflight_threads

* Update CODEOWNERS and remove serialize submit option
This commit is contained in:
Reese Levine
2025-10-07 13:48:56 -07:00
committed by GitHub
parent aeaf8a36f0
commit 74b8fc17f9
6 changed files with 518 additions and 250 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-webgpu/wgsl-shaders/mul_mat.tmpl.wgsl
+1 -1
View File
@@ -870,7 +870,7 @@ struct MulMatParams {
@group(0) @binding(3) var<uniform> params: MulMatParams;
@compute @workgroup_size(64)
@compute @workgroup_size(256)
fn main(@builtin(global_invocation_id) global_id: vec3<u32>) {
let total = params.m * params.n * params.bs02 * params.broadcast2 * params.bs03 * params.broadcast3;
if (global_id.x >= total) {