llama.cpp
llama : reorganize source code + improve CMake
#8006
Merged
Overview
Commits
13
Changes
View On GitHub
Commits
  • scripts : update sync [no ci]
    ggerganov committed 336 days ago
  • files : relocate [no ci]
    ggerganov committed 336 days ago
  • ci : disable kompute build [no ci]
    ggerganov committed 336 days ago
  • cmake : fixes [no ci]
    ggerganov committed 336 days ago
  • server : fix mingw build
    ggerganov committed 336 days ago
  • cmake : minor [no ci]
    ggerganov committed 336 days ago
  • cmake : link math library [no ci]
    ggerganov committed 336 days ago
  • cmake : build normal ggml library (not object library) [no ci]
    ggerganov committed 336 days ago
  • cmake : fix kompute build
    ggerganov committed 336 days ago
  • make,cmake : fix LLAMA_CUDA + replace GGML_CDEF_PRIVATE
    ggerganov committed 336 days ago
  • move public backend headers to the public include directory (#8122)
    ggerganov committed 336 days ago
  • scripts : fix sync paths [no ci]
    ggerganov committed 336 days ago
  • scripts : sync ggml-blas.h [no ci]
    ggerganov committed 336 days ago
  • scripts
    • File
      sync-ggml-am.sh
    • File
      sync-ggml.sh

Loading comments...

FAQ Terms Privacy Refunds Impressum
Loading