]> git.djapps.eu Git - pkg/ggml/sources/whisper.cpp/commit
ggml-zendnn : adaptive fallback to CPU backend for small batch sizes (llama/22681)
authorSachin Sharma <redacted>
Wed, 13 May 2026 06:13:47 +0000 (11:43 +0530)
committerGeorgi Gerganov <redacted>
Thu, 14 May 2026 18:26:48 +0000 (21:26 +0300)
commit8b288f5d966e3b3fb048097e991bdb815e79caf6
tree6235a5fcaad0e85a84c0086a4f2356b6ebb21c1a
parentbcaf4498269fea44b47621a4f0e8dff562c93cd4
ggml-zendnn : adaptive fallback to CPU backend for small batch sizes (llama/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
ggml/src/ggml-zendnn/ggml-zendnn.cpp