llama.cpp
ggml-zendnn : adaptive fallback to CPU backend for small batch sizes
#22681
Merged
Merged
ggml-zendnn : adaptive fallback to CPU backend for small batch sizes #22681
ggerganov
merged
2 commits into
ggml-org:master
from
z-sachin:ggml-zendnn/adaptive-fallback-env
ggml-zendnn : add runtime env var GGML_ZENDNN_ADAPTIVE_FALLBACK to co…
a38a4ca6
ggml-zendnn : restore original fallback logic when adaptive fallback …
199e8f29
z-vishal
approved these changes
on 2026-05-12
taronaeo
approved these changes
on 2026-05-12
am17an
approved these changes
on 2026-05-12
lhez
approved these changes
on 2026-05-12
Login to write a write a comment.
Login via GitHub