llama.cpp
sync : ggml
#12104
Merged
Overview
Commits
11
Changes
View On GitHub
Commits
  • scripts : sync-ggml-am.sh fix
    ggerganov committed 1 year ago
  • Support pure float16 add/sub/mul/div operations in the CUDA (and CPU) backend (ggml/1121)
    ggerganov committed 1 year ago
  • Told cmake to install ggml-cpp.h as a public header file. (ggml/1126)
    ggerganov committed 1 year ago
  • cmake : fix compile assumptions for power9/etc (whisper/2777)
    ggerganov committed 1 year ago
  • whisper : support GGML_BACKEND_DL (whisper/2843)
    ggerganov committed 1 year ago
  • cuda/cpu: Increase support for fp16 unary operations (ggml/1125)
    ggerganov committed 1 year ago
  • sync : ggml
    ggerganov committed 1 year ago
  • cuda/vulkan: specify fp32-only support for some operations in supports_op (ggml/1129)
    ggerganov committed 1 year ago
  • sync : ggml
    ggerganov committed 1 year ago
  • cuda: unary ops as float + de-duplicate (ggml/1130)
    ggerganov committed 1 year ago
  • sync : ggml
    ggerganov committed 1 year ago
FAQ Terms Privacy Refunds Impressum
Loading