git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit

]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit

overview / pkg / ggml / sources / llama.cpp / commit

author	Masashi Yoshimura <redacted>
	Tue, 23 Jun 2026 08:13:55 +0000 (17:13 +0900)
committer	GitHub <redacted>
	Tue, 23 Jun 2026 08:13:55 +0000 (17:13 +0900)
commit	7c908502ea0868e6ae913f79ba84ba844a5b386a
tree	aa8abcb5af60bf2a6c66e0b517709f98cd2ac152	tree
parent	035cd8f9a6dda9cd0224b07d3df2dc95f7a3a31e	commit \| diff

ggml-webgpu: improve MTP inference by using mat-vec path for small batches (#24811)

* ggml-webgpu: improve small batches decoding

* Add barrier to the NUM_COLS loop in mul-mat-vec

Packaging of ggml-org/llama.cpp

RSS Atom

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/mul_mat_id_vec.wgsl		diff \| blob \| history
ggml/src/ggml-webgpu/wgsl-shaders/mul_mat_vec.wgsl		diff \| blob \| history
ggml/src/ggml-webgpu/wgsl-shaders/mul_mat_vec_acc.tmpl		diff \| blob \| history
ggml/src/ggml-webgpu/wgsl-shaders/mul_mat_vec_q_acc.tmpl		diff \| blob \| history
ggml/src/ggml-webgpu/wgsl-shaders/quantize_q8.wgsl		diff \| blob \| history
tests/test-backend-ops.cpp		diff \| blob \| history