llama.cpp
ggml-webgpu: Enable NVIDIA self-hosted CI
#22976
Merged

ggml-webgpu: Enable NVIDIA self-hosted CI #22976

reeselevine
github-actions github-actions added devops
github-actions github-actions added testing
github-actions github-actions added ggml
github-actions github-actions added WebGPU
reeselevine Enabel nvidia ci for webgpu
a6711b2b
reeselevine Address precision issues
6ff207e6
reeselevine fix placement
0b7d0009
reeselevine Relax more set_rows and div
27a49937
reeselevine Try relaxing all f16
7112fc33
reeselevine reeselevine force pushed from d90db229 to 7112fc33 50 days ago
reeselevine formatting and naming
5761ea26
reeselevine reeselevine marked this pull request as ready for review 49 days ago
reeselevine reeselevine requested a review from ggerganov ggerganov 49 days ago
reeselevine reeselevine requested a review 49 days ago
reeselevine reeselevine requested a review from CISC CISC 49 days ago
taronaeo
taronaeo approved these changes on 2026-05-14
CISC
CISC approved these changes on 2026-05-14
reeselevine Add comment explaining max_nmse_err logic
350ff803
CISC
CISC approved these changes on 2026-05-14
reeselevine reeselevine merged 834a2436 into master 49 days ago

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
Milestone