Home Explore Help
Sign In
cturan
/
llama.cpp
mirror of https://github.com/cturan/llama.cpp
1
0
Fork 0
Files Issues 0 Wiki
Tree: 4f41ee11d6
Branches Tags

Commit History

Author SHA1 Message Date
  David Huang 7f323a589f Add `--no-op-offload` to improve `-ot` pp perf in MoE models like llama4 400B (#13386) 8 months ago
  fairydreaming 8fcb563613 Load all MoE experts during warmup (#11571) 10 months ago
  Georgi Gerganov f66f582927 llama : refactor `src/llama.cpp` (#10902) 1 year ago