llama.cpp
CANN: support gated linear attn
#18653
Open

CANN: support gated linear attn #18653

hipudding wants to merge 2 commits into ggml-org:master from hipudding:gla
hipudding
hipudding hipudding marked this pull request as draft 5 days ago
github-actions github-actions added ggml
github-actions github-actions added Ascend NPU
hipudding hipudding force pushed from 7c21f715 to 81f18f3c 5 days ago
CANN: support gated linear attn
8c51ace7
hipudding CANN: optimize OP gla
746a693d
hipudding hipudding force pushed from 81f18f3c to 746a693d 5 days ago
hipudding
hipudding hipudding marked this pull request as ready for review 5 days ago
hipudding hipudding requested a review from noemotiovon noemotiovon 5 days ago
noemotiovon
noemotiovon approved these changes on 2026-01-07

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
Milestone