whisper.cpp/ggml
Noah 52e43a2fa5 Fix garbled output with REPACK at high thread counts (llama/16956)
* 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>
2025-11-09 23:38:03 +02:00
..
cmake ggml: Skip backend library linking code when GGML_BACKEND_DL=ON (llama/15094) 2025-08-18 20:30:45 +03:00
include model: add support for qwen3vl series (llama/16780) 2025-11-09 23:38:03 +02:00
src Fix garbled output with REPACK at high thread counts (llama/16956) 2025-11-09 23:38:03 +02:00
.gitignore whisper : reorganize source code + improve CMake (#2256) 2024-06-26 19:34:09 +03:00
CMakeLists.txt Add experimental ggml-hexagon backend for the Hexagon NPU (llama/16547) 2025-11-09 23:38:03 +02:00