llama.cpp
hexagon: support for UPSCALE op
#31331
Merged
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Overview
Commits
6
Changes
View On
GitHub
hexagon: support for UPSCALE op
#31331
max-krasnyansky
merged 6 commits into
ggml-org:master
from
qualcomm:hexagon-upscale-op
hex-upscale: basic upscale ops (not fully vectorized)
5d609a71
hex-upscale: optimize nearest 2x, 4x and bilinear 4x
4e61c2c7
hex-upscale: add support for non-contig rows and dims collapsing
8c945696
hex-upscale: use vgather instead of scalar staging
413a40d3
hex-upscale: move all kernel select logic to the host, review comment…
0804f941
tests: add permuted UPSCALE test to cover qwen3-vl image->text scenarios
137be776
max-krasnyansky
requested a review
from
ggerganov
11 days ago
max-krasnyansky
requested a review
11 days ago
github-actions
added
testing
github-actions
added
ggml
github-actions
added
Hexagon
lhez
approved these changes on 2026-10-28
max-krasnyansky
added
merge ready
jhen0409
approved these changes on 2026-10-29
max-krasnyansky
merged
8a199ad3
into master
10 days ago
Login to write a write a comment.
Login via GitHub
Reviewers
jhen0409
lhez
ggerganov
Assignees
No one assigned
Labels
testing
ggml
merge ready
Hexagon
Milestone
No milestone
Login to write a write a comment.
Login via GitHub