sdgoij/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-03-17 16:44:07 +00:00
Code Issues Packages Projects Releases Wiki Activity

ggml-webgpu: improve flastAttention performance by software pipelining (#19151)

Browse Source 
* webgpu : pipeline flash_attn Q/K loads in WGSL

* ggml-webgpu: unroll Q*K accumlation inner loop

* ggml-webgpu: vectorization

* ggml-webgpu: unrolling

* ggml-webgpu: remove redundant unrolling

* ggml-webgpu: restore the config

* ggml-webgpu: remove redundant comments

* ggml-webgpu: formatting

* ggml-webgpu: formatting and remove vectorization

* ggml-webgpu: remove unnecessary constants

* ggml-webgpu: change QKV buffer to read_write to pass validation

* ggml-webgpu: add explanation for the additional bracket around Q K accumulate

* Indentation and for -> if for tail

* Kick off CI on wgsl only commits

---------

Co-authored-by: Reese Levine <reeselevine1@gmail.com>
This commit is contained in:
Zheyuan Chen
2026-01-29 14:05:30 -08:00
committed by GitHub
parent ce38a4db47
commit bd90fc74c3
2 changed files with 109 additions and 62 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
.github/workflows/build.yml vendored
View File

@@ -21,7 +21,8 @@ on:
'**/*.m',
'**/*.metal',
'**/*.comp',
'**/*.glsl'
'**/*.glsl',
'**/*.wgsl'
]
pull_request:
@@ -42,7 +43,8 @@ on:
'**/*.m',
'**/*.metal',
'**/*.comp',
'**/*.glsl'
'**/*.glsl',
'**/*.wgsl'
]
concurrency: