]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 299f5d7)
ggml webgpu: faster matrix multiplication/matrix-vector multiplication (#17031)
authorReese Levine <redacted>
Sat, 8 Nov 2025 03:27:20 +0000 (19:27 -0800)
committerGitHub <redacted>
Sat, 8 Nov 2025 03:27:20 +0000 (19:27 -0800)
commit647b960bd8017ee882d6633bc2e43e2ae82ee85c
tree412a913ff8a9ad530c8c2c207a4b8213ddfa3699tree
parent299f5d782c8ffd7195a1ed6a6d5561f759beb07ecommit | diff
ggml webgpu: faster matrix multiplication/matrix-vector multiplication (#17031)

* Faster tensors (#8)

Add fast matrix and matrix/vector multiplication.

* Use map for shader replacements instead of pair of strings
.github/workflows/build.yml diff | blob | history
ggml/src/ggml-webgpu/ggml-webgpu.cpp diff | blob | history
ggml/src/ggml-webgpu/wgsl-shaders/embed_wgsl.py diff | blob | history
ggml/src/ggml-webgpu/wgsl-shaders/mul_mat.tmpl.wgsl diff | blob | history
ggml/src/ggml-webgpu/wgsl-shaders/mul_mat_decls.tmpl [new file with mode: 0644] blob
ggml/src/ggml-webgpu/wgsl-shaders/mul_mat_reg_tile.tmpl.wgsl [new file with mode: 0644] blob
ggml/src/ggml-webgpu/wgsl-shaders/mul_mat_subgroup_matrix.tmpl.wgsl [new file with mode: 0644] blob
ggml/src/ggml-webgpu/wgsl-shaders/mul_mat_vec.tmpl.wgsl [new file with mode: 0644] blob
Packaging of ggml-org/llama.cpp