mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2025-11-08 10:07:01 +00:00
1f5accb8d0
* Fix garbled output with REPACK at high thread counts Fixed a race condition in the REPACK matrix multiplication code that caused garbled output when using 26+ threads (model-dependent threshold). The issue occurred because with high thread counts, the code forced chunk count to equal thread count, creating many small chunks. After aligning these chunks to NB_COLS boundaries, adjacent chunks could overlap, causing data corruption and race conditions. The fix enforces minimum chunk sizes based on NB_COLS and caps maximum chunk count to prevent creating too many tiny chunks, ensuring proper alignment without overlaps. * Update ggml/src/ggml-cpu/repack.cpp Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> * Update ggml/src/ggml-cpu/repack.cpp Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
79 KiB
79 KiB