CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-02 09:12:03 +00:00
Code Issues Packages Projects Releases Wiki Activity
Files
ebd062bc19b92ff9860a12e4f789b305015fb18b
llama.cpp/ggml-cuda.cu
Georgi Gerganov ebd062bc19 cuda : use 512 threads for soft_max instead of 32
2023-11-30 18:07:51 +02:00

312 KiB
Raw Blame History

View Raw
Reference in New Issue View Git Blame Copy Permalink