llama.cpp
0fd13e94 - Merge branch 'master' into compilade/refactor-kv-cache
Commit
View On GitHub
Comment changes are shownComment changes are hidden
Commit
1 year ago
Merge branch 'master' into compilade/refactor-kv-cache
Author
compilade compilade
  • .github
    • File
      labeler.yml
    • workflows
      • File
        docker.yml
  • File
    CMakeLists.txt
  • File
    Makefile
  • File
    README.md
  • ci
    • File
      run.sh
  • File
    convert-hf-to-gguf.py
  • examples
    • finetune
      • File
        finetune.cpp
    • main
      • File
        main.cpp
    • sycl
      • File
        win-build-sycl.bat
    • train-text-from-scratch
      • File
        train-text-from-scratch.cpp
  • File
    flake.lock
  • File
    ggml-common.h
  • ggml-cuda
    • File
      convert.cu
    • File
      dmmv.cu
    • File
      fattn-tile-f16.cu
    • File
      fattn-tile-f32.cu
    • File
      fattn-vec-f16.cu
    • File
      fattn-vec-f32.cu
    • File
      mmq.cu
    • File
      vecdotq.cuh
  • File
    ggml-metal.m
  • ggml-metal.metal
  • File
    ggml-opencl.cpp
  • File
    ggml-quants.c
  • File
    ggml-sycl.cpp
  • File
    ggml-vulkan-shaders.hpp
  • File
    ggml-vulkan.cpp
  • File
    ggml.c
  • File
    ggml.h
  • File
    ggml_vk_generate_shaders.py
  • gguf-py/gguf
    • File
      constants.py
    • File
      tensor_mapping.py
  • File
    llama.cpp
  • File
    llama.h
  • tests
    • File
      test-chat-template.cpp
    • File
      test-grad0.cpp
FAQ Terms Privacy Refunds Impressum