llama.cpp
opencl: fix for small models
#11950
Merged

opencl: fix for small models #11950

lhez
shawngu-quic opencl: fix small shape gemv, remove unused extensions
b0a765c0
quic-sszot opencl: fix `transpose_16`, `dump_tensor`, enforce subgroup size
097f8690
quic-sszot opencl: fix for token length < 4
97151f42
quic-sszot opencl: use wave size of 64 for all Adreno GPUs
d55ea5ee
github-actions github-actions added ggml
lhez lhez marked this pull request as ready for review 262 days ago
max-krasnyansky
max-krasnyansky approved these changes on 2025-02-24
max-krasnyansky max-krasnyansky merged 34a846b5 into master 256 days ago

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
Milestone