mirror of https://github.com/google/gemma.cpp.git
Previously, this happened concurrently with the matmul autotune, which could lead to incorrect outcomes. threading: de-singleton Pinning (no longer stores affinity); pass PoolWorkerMapping; fix Pool dtor order Also enable SPR target (Zen4 is AMD-only), update Highway version for renamed Thread()->GlobalIdx(). PiperOrigin-RevId: 816223017 |
||
|---|---|---|
| .. | ||
| python | ||
| BUILD.bazel | ||
| analyze.h | ||
| compress-inl.h | ||
| compress.cc | ||
| compress.h | ||
| compress_test.cc | ||
| distortion.h | ||
| distortion_test.cc | ||
| nuq-inl.h | ||
| nuq_test.cc | ||
| sfp-inl.h | ||
| sfp_test.cc | ||
| test_util-inl.h | ||
| types.h | ||