llama.cpp
ggml-hexagon: gelu operation
#17921
Merged

ggml-hexagon: gelu operation #17921

joeldushouyu
joeldushouyu feat: inital support for gelu using sigmoid approximation
83412e0b
github-actions github-actions added ggml
joeldushouyu snapshot: faster gelu using polynomial approximation
2a787a61
joeldushouyu
joeldushouyu test: disable l2-block prefetch in polynomail approximation
72339994
joeldushouyu
joeldushouyu Revert "test: disable l2-block prefetch in polynomail approximation"
470b4991
joeldushouyu Revert "snapshot: faster gelu using polynomial approximation"
999492fe
joeldushouyu debug: temporarily disable unnecessary log message for debug purpose
84f2f23a
joeldushouyu Feat: optiized unaligned sigmoid_f32
fc2289dc
joeldushouyu
joeldushouyu Feat: larger l2prefetch block
8bc299dd
joeldushouyu feat: apply unaligned-load optimization on mul and mul_scalar
cbd4e932
joeldushouyu
max-krasnyansky
max-krasnyansky
joeldushouyu
joeldushouyu Revert "debug: temporarily disable unnecessary log message for debug …
e51b6bf2
joeldushouyu refactor: cleanup commented unused code
05693357
joeldushouyu chore: reformat code with clang-formatter to pass cli test
952877ec
joeldushouyu joeldushouyu marked this pull request as ready for review 35 days ago
joeldushouyu joeldushouyu requested a review from max-krasnyansky max-krasnyansky 35 days ago
joeldushouyu joeldushouyu requested a review from lhez lhez 35 days ago
max-krasnyansky
joeldushouyu Revert "chore: reformat code with clang-formatter to pass cli test"
cf3a65fb
joeldushouyu
max-krasnyansky
max-krasnyansky
joeldushouyu
joeldushouyu fix: fix loop overflow
52f43fb9
joeldushouyu
max-krasnyansky
max-krasnyansky
max-krasnyansky approved these changes on 2025-12-16
max-krasnyansky
joeldushouyu chore: fix formating ci error
15ef64b3
joeldushouyu
max-krasnyansky
max-krasnyansky max-krasnyansky merged 4470a076 into master 34 days ago

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
Milestone