happyz
/
llama.cpp
mirror of https://github.com/ggerganov/llama.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
llama.cpp/.github/workflows
History
Zheyuan Chen bd90fc74c3
ggml-webgpu: improve flastAttention performance by software pipelining (#19151) 
* 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>
 		2026-01-29 14:05:30 -08:00
..
bench.yml.disabled llama : move end-user examples to tools directory (#13249) 2025-05-02 20:27:13 +02:00
build-cache.yml ci : update GitHub Actions versions [no ci] (#18935) 2026-01-22 00:57:18 +01:00
build-cmake-pkg.yml ci : update GitHub Actions versions [no ci] (#18935) 2026-01-22 00:57:18 +01:00
build-linux-cross.yml ci : update GitHub Actions versions [no ci] (#18935) 2026-01-22 00:57:18 +01:00
build.yml ggml-webgpu: improve flastAttention performance by software pipelining (#19151) 2026-01-29 14:05:30 -08:00
check-vendor.yml ci : use new 1vCPU runner for lightweight jobs (#19107) 2026-01-26 15:22:49 +01:00
close-issue.yml ci : use new 1vCPU runner for lightweight jobs (#19107) 2026-01-26 15:22:49 +01:00
copilot-setup-steps.yml ci : update GitHub Actions versions [no ci] (#18935) 2026-01-22 00:57:18 +01:00
docker.yml ci : update GitHub Actions versions [no ci] (#18935) 2026-01-22 00:57:18 +01:00
editorconfig.yml ci : use new 1vCPU runner for lightweight jobs (#19107) 2026-01-26 15:22:49 +01:00
gguf-publish.yml ci : use new 1vCPU runner for lightweight jobs (#19107) 2026-01-26 15:22:49 +01:00
labeler.yml ci : use new 1vCPU runner for lightweight jobs (#19107) 2026-01-26 15:22:49 +01:00
pre-tokenizer-hashes.yml ci : use new 1vCPU runner for lightweight jobs (#19107) 2026-01-26 15:22:49 +01:00
python-check-requirements.yml ci : use new 1vCPU runner for lightweight jobs (#19107) 2026-01-26 15:22:49 +01:00
python-lint.yml ci : use new 1vCPU runner for lightweight jobs (#19107) 2026-01-26 15:22:49 +01:00
python-type-check.yml ci : use new 1vCPU runner for lightweight jobs (#19107) 2026-01-26 15:22:49 +01:00
release.yml release: update github api (#19022) 2026-01-22 21:38:02 +08:00
server-webui.yml ci : update GitHub Actions versions [no ci] (#18935) 2026-01-22 00:57:18 +01:00
server.yml graph : utilize `ggml_build_forward_select()` to avoid reallocations (#18898) 2026-01-23 18:22:34 +02:00
update-ops-docs.yml ci : use new 1vCPU runner for lightweight jobs (#19107) 2026-01-26 15:22:49 +01:00
winget.yml ci : find latest release with asset for winget (#19161) 2026-01-28 22:05:39 +01:00