llama.cpp/tests/CMakeLists.txt at 021cc28bef4dd7d0bf9c91dbbd0803caa6cb15f2

mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-01 09:01:57 +00:00

Files

Diego Devesa 6adc3c3ebc llama : add thread safety test (#14035 )

* llama : add thread safety test

* llamafile : remove global state

* llama : better LLAMA_SPLIT_MODE_NONE logic

when main_gpu < 0 GPU devices are not used

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

2025-06-16 08:11:43 -07:00

9.3 KiB

Raw Blame History

View Raw

9.3 KiB Raw Blame History

9.3 KiB

Raw Blame History