llama.cpp
webgpu: add MMVQ support for Q1_0/Q5_0/Q5_1/Q3_K/Q5_K/Q6_K/MXFP4
#29483
Merged

webgpu: add MMVQ support for Q1_0/Q5_0/Q5_1/Q3_K/Q5_K/Q6_K/MXFP4 #29483

yomaytk
yomaytk yomaytk requested a review 13 days ago
yomaytk
yomaytk commented on 2026-09-26
yomaytk
yomaytk commented on 2026-09-26
yomaytk yomaytk requested a review from CISC CISC 13 days ago
github-actions github-actions added ggml
github-actions github-actions added WebGPU
CISC
CISC approved these changes on 2026-09-26
yomaytk yomaytk added merge ready
yomaytk yomaytk removed merge ready
yomaytk yomaytk force pushed from c4c735c3 to 12a7b37e 10 days ago
yomaytk yomaytk force pushed from 12a7b37e to 4def9481 8 days ago
yomaytk yomaytk force pushed from 825b67e0 to 4d5c4139 6 days ago
yomaytk add supports for q1/q5/q3_k/q5_k/q6_k/mxfp4 of mmvq path
d5153a42
yomaytk Add K_QUANTS_HANDLING macro to q1_0 of mmvq path
4d5c4139
yomaytk
CISC CISC merged 8216c846 into master 4 days ago

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
Milestone