llama.cpp
hexagon: n_hvx and n_threads cleanup
#31857
Merged
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Overview
Commits
8
Changes
View On
GitHub
hexagon: n_hvx and n_threads cleanup
#31857
max-krasnyansky
merged 8 commits into
ggml-org:master
from
qualcomm:hexagon-nhvx-cleanup
hex-nhvx: apply nhvx updates to the latest master
0bd04afc
hex-nhvx: set N_HVX and N_THREADS based on the arch to avoid overallo…
17a9d3a9
hex-build: add support for enabling HTP_DEBUG via build.py
8c665ba2
hex-trace: move tracing state/helpers into new htp-trace.h header
8b120fe8
hex-dcache: cleanup dcache #defines
cef75470
github-actions
added
documentation
github-actions
added
ggml
github-actions
added
Hexagon
hex-hnvx: minimize the diff by reflowing the macros
bc9c157e
hex-ci: fix python type/linter warnings
08db3f8f
hex-nhvx: consitent logging
1deb637f
max-krasnyansky
marked this pull request as ready for review
3 days ago
max-krasnyansky
requested a review
3 days ago
max-krasnyansky
added
merge ready
lhez
approved these changes on 2026-11-07
jhen0409
approved these changes on 2026-11-07
max-krasnyansky
merged
e9a2a44f
into master
2 days ago
Login to write a write a comment.
Login via GitHub
Reviewers
jhen0409
lhez
Assignees
No one assigned
Labels
documentation
ggml
merge ready
Hexagon
Milestone
No milestone
Login to write a write a comment.
Login via GitHub