]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 192d8ae)
[WebGPU] Check batch_compute_passes before sending passes when not doing GPU profilin...
authorNikhil Jain <redacted>
Tue, 26 May 2026 03:32:49 +0000 (20:32 -0700)
committerGitHub <redacted>
Tue, 26 May 2026 03:32:49 +0000 (20:32 -0700)
commit54121f7325ff0662b4042dc7c7da6249428d72ee
tree0036c2b57aebfa997a78faffab3d7291bda5725ctree
parent192d8ae8b8826642f15836570b944ecd68cf175ccommit | diff
[WebGPU] Check batch_compute_passes before sending passes when not doing GPU profiling (#23457)

* Only run webgpu CI on my fork

* Add webgpu only workflow

* refactor batch_compute_passes to a per-thread variable, and submit individual passes when it is set to false and no GPU profiling is enabled

* restore build.yml
ggml/src/ggml-webgpu/ggml-webgpu.cpp diff | blob | history
Packaging of ggml-org/llama.cpp