]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 856c3ad)
ggml-zendnn : adaptive fallback to CPU backend for small batch sizes (#22681)
authorSachin Sharma <redacted>
Wed, 13 May 2026 06:13:47 +0000 (11:43 +0530)
committerGitHub <redacted>
Wed, 13 May 2026 06:13:47 +0000 (09:13 +0300)
commit61af07c22df7e06d07905a74f39d3809e6c0522f
treeb36ba155c8f217b7419b691d9495e330f51efd43tree
parent856c3adac1709be15e1ea2529a0e89f742d25fe0commit | diff
ggml-zendnn : adaptive fallback to CPU backend for small batch sizes (#22681)

* ggml-zendnn : add runtime env var GGML_ZENDNN_ADAPTIVE_FALLBACK to control adaptive fallback (default: enabled)

* ggml-zendnn : restore original fallback logic when adaptive fallback is disabled
ggml/src/ggml-zendnn/CMakeLists.txt diff | blob | history
ggml/src/ggml-zendnn/ggml-zendnn.cpp diff | blob | history
Packaging of ggml-org/llama.cpp