sdgoij/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-05-12 20:14:09 +00:00
Code Issues Packages Projects Releases Wiki Activity
Files
a84dfd3e1072bcf422b90dc4b03d334395c90fe4
llama.cpp/tests/test-backend-ops.cpp
Oliver Simons a84dfd3e10 CUDA: Add Cooperative-Groups-based parallelization of ncols in softmax 
Old implementation parallelizes rows across SMs, which does not fit the
needs of backend-sampling (where we have ncols >> nrows and thus want to
parallelize ncols across SMs)
2025-12-09 12:58:56 +01:00

327 KiB
Raw Blame History

View Raw
Reference in New Issue View Git Blame Copy Permalink