llama.cpp
ggml webgpu: faster matrix multiplication/matrix-vector multiplication
#17031

Merged

ggml webgpu: faster matrix multiplication/matrix-vector multiplication #17031

reeselevine merged 2 commits into ggml-org:master from reeselevine:master

Faster tensors (#8)

c6bc1259

reeselevine requested a review from

CISC 302 days ago

github-actions added python

github-actions added devops

github-actions added ggml

CISC commented on 2025-11-05

ngxson approved these changes on 2025-11-06

Use map for shader replacements instead of pair of strings

7c2b2ef2

reeselevine merged 647b960b into master 299 days ago

Reviewers

ngxson

CISC

Assignees

No one assigned

Labels

python devops ggml

Milestone

No milestone