]> git.djapps.eu Git - pkg/ggml/sources/whisper.cpp/commit
overview / pkg / ggml / sources / whisper.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 931cf2f)
ggml-webgpu: updated matrix-vector multiplication (llama/21738)
authorneha-ha <redacted>
Mon, 20 Apr 2026 14:37:17 +0000 (07:37 -0700)
committerGeorgi Gerganov <redacted>
Thu, 30 Apr 2026 08:29:13 +0000 (11:29 +0300)
commit5f21fdcbb9400721732c161e4b04174e5d8625db
treecb76c35ffa81737678081e81357134e51382128atree
parent931cf2f3a81af3f347cc01bed686d374c851a2e4commit | diff
ggml-webgpu: updated matrix-vector multiplication (llama/21738)

* merged properly, but slow q3_k and q5_k with u32 indexing

* Start on new mat-vec

* New format float paths working

* Working q4_0

* Work on remaining legacy q-types

* port k-quants to new matvec

* remove old shader

* Remove old constants, format

* remove accidental file

---------

Co-authored-by: Neha Abbas <redacted>
Co-authored-by: Reese Levine <redacted>
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/common_decls.tmpl diff | blob | history
ggml/src/ggml-webgpu/wgsl-shaders/mul_mat_vec.wgsl diff | blob | history
Packaging of ggerganov/whisper.cpp