]> git.djapps.eu Git - pkg/ggml/sources/whisper.cpp/commit
overview / pkg / ggml / sources / whisper.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 2307712)
Check batch_compute_passes before sending passes when not doing GPU profiling (llama...
authorNikhil Jain <redacted>
Tue, 26 May 2026 03:32:49 +0000 (20:32 -0700)
committerGeorgi Gerganov <redacted>
Fri, 29 May 2026 06:47:30 +0000 (09:47 +0300)
commitbc77933c2de8c5d104bfc234e3358217265fe147
treed28ce7bc20626888dcc1514ce5fa6a17493c9caetree
parent2307712d32a17becc38f6efb8154be5196aa8f87commit | diff
Check batch_compute_passes before sending passes when not doing GPU profiling (llama/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 ggerganov/whisper.cpp