]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 030ebb5)
ggml-webgpu: fix CI errors from #25025 and #25262 (#26566)
authorMasashi Yoshimura <redacted>
Tue, 11 Aug 2026 04:10:00 +0000 (13:10 +0900)
committerGitHub <redacted>
Tue, 11 Aug 2026 04:10:00 +0000 (07:10 +0300)
commit84f712946729f8517c972da4eb80db810ffe3210
tree6066c8ebce2521377c7a99dabdd4a111b5120574tree
parent030ebb558a5820b444a8f836ed5cdd46c9b4bd7acommit | diff
ggml-webgpu: fix CI errors from #25025 and #25262 (#26566)

* test new flash_attn test

* rebase and fix to disable subgrou matrices when max_kv_tile == 0

* delete log output

* Add i32 support to cpy and enables the all ops test

* restore the non target ci tests

* comment out of TODO of build-cpu.yml

* fix format
ggml/src/ggml-webgpu/ggml-webgpu-shader-lib.hpp diff | blob | history
ggml/src/ggml-webgpu/ggml-webgpu.cpp diff | blob | history
ggml/src/ggml-webgpu/wgsl-shaders/cpy.wgsl diff | blob | history
Packaging of ggml-org/llama.cpp