llama.cpp
ggml-webgpu: add Q1_0 support
#22374
Merged

ggml-webgpu: add Q1_0 support #22374

SharmaRithik
SharmaRithik SharmaRithik requested a review 95 days ago
github-actions github-actions added ggml
github-actions github-actions added WebGPU
SharmaRithik add fast matmul matvec q1_0 kernel
0c4b40ed
SharmaRithik SharmaRithik force pushed from a3555392 to 0c4b40ed 95 days ago
CISC
CISC approved these changes on 2026-04-26
Aflah012
Aflah012 approved these changes on 2026-04-26
reeselevine
reeselevine commented on 2026-04-27
reeselevine
reeselevine commented on 2026-04-27
SharmaRithik ggml-webgpu: drop redundant zero-fills in Q1_0 shmem init
18e1122e
SharmaRithik
reeselevine
reeselevine approved these changes on 2026-04-27
reeselevine reeselevine merged 434b2a1f into master 93 days ago

Login to write a write a comment.

Login via GitHub

Assignees
No one assigned
Labels
Milestone