llama.cpp
a9681feb - ggml : online attention (CPU)

Commit
1 year ago
ggml : online attention (CPU)
Author
Committer
Parents
  • File
    ggml-metal.m
  • ggml-metal.metal
  • File
    ggml.c
  • File
    ggml.h
  • File
    llama.cpp
  • tests
    • File
      test-backend-ops.cpp