llama.cpp
ggml-webgpu: fast matrix-vector multiplication for i-quants
#22344

Merged

ggml-webgpu: fast matrix-vector multiplication for i-quants #22344

reeselevine merged 1 commit into ggml-org:master from SharmaRithik:webgpu-matvec-iq-fast

add fast mat-vec kernels for i-quants

e85876c9

SharmaRithik requested a review 82 days ago

github-actions added ggml

github-actions added WebGPU

CISC approved these changes on 2026-04-25

reeselevine approved these changes on 2026-04-27

reeselevine merged 665abc60 into master 79 days ago

Reviewers

reeselevine

CISC

Assignees

No one assigned

Labels

ggml WebGPU

Milestone

No milestone