]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 8bccdbb)
ggml-webgpu: Add fused RMS_NORM + MUL (#21983)
authorMasashi Yoshimura <redacted>
Wed, 22 Apr 2026 17:51:40 +0000 (02:51 +0900)
committerGitHub <redacted>
Wed, 22 Apr 2026 17:51:40 +0000 (10:51 -0700)
commit6da7168312a01da0f1ea50c8eb909340bb192c4e
tree40fdc425b6bc914a65fb477c42bd73bdfcc550f5tree
parent8bccdbbff9d0d91d54838471f6eea182b9ab1b79commit | diff
ggml-webgpu: Add fused RMS_NORM + MUL (#21983)

* fused rms_norm_mul + mul

* Add GGML_WEBGPU_DISABLE_FUSION for being able to disable kernel fusion.

* Decouple num_fused_ops from webgpu_context; misc cleanup

* Fix eps handling and remove disable_fusion.

* Fix not to use c++20 initializers.
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/rms_norm_mul.wgsl [new file with mode: 0644] blob
Packaging of ggml-org/llama.cpp