llama.cpp
ggml-webgpu: add q4_0/q8_0 SET_ROWS
#23760
Merged

ggml-webgpu: add q4_0/q8_0 SET_ROWS #23760

reeselevine
reeselevine Add q8_0 and q4_0 set_rows
00d3b17e
reeselevine Add fast(er) quantization set_rows path
12910a91
reeselevine formatting/naming
91d3a3c8
reeselevine a little more naming
27ca5506
reeselevine reeselevine requested a review 65 days ago
github-actions github-actions added ggml
github-actions github-actions added WebGPU
yomaytk
yomaytk commented on 2026-05-27
yomaytk
reeselevine Remove unused constant
338b57ad
reeselevine Merge remote-tracking branch 'upstream/master' into q_set_rows
d30666ae
reeselevine reeselevine requested a review from ggerganov ggerganov 64 days ago
github-actions github-actions added testing
reeselevine
reeselevine commented on 2026-05-27
reeselevine Don't override other override
acf393b3
reeselevine reeselevine added merge ready
reeselevine reeselevine requested a review from CISC CISC 64 days ago
CISC
CISC approved these changes on 2026-05-28
ggerganov
ggerganov commented on 2026-05-28
reeselevine reeselevine removed merge ready
reeselevine Avoid bitcast
64c3e988
reeselevine
reeselevine Narrow relaxation
e221316a
ggerganov
ggerganov approved these changes on 2026-05-29
reeselevine reeselevine merged b22da258 into master 62 days ago

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
Milestone