Commit History

Author SHA1 Message Date
  Georgi Gerganov 381da2d9f0 metal : build metallib + fix embed path (#6015) 1 year ago
  slaren f30ea47a87 llama : add pipeline parallelism support (#6017) 1 year ago
  Georgi Gerganov 83796e62bc llama : refactor unicode stuff (#5992) 1 year ago
  DAN™ bcebd7dbf6 llama : add support for GritLM (#5959) 1 year ago
  Georgi Gerganov 8a3012a4ad ggml : add ggml-common.h to deduplicate shared code (#5940) 1 year ago
  Gabe Goodhart e1fa9569ba server : add SSL support (#5926) 1 year ago
  Georgi Gerganov 2002bc96bf server : refactor (#5882) 1 year ago
  le.chang cbbd1efa06 Makefile: use variables for cublas (#5689) 1 year ago
  kwin1412 f1a98c5254 make : fix nvcc version is empty (#5713) 1 year ago
  CJ Pais 6560bed3f0 server : support llava 1.6 (#5553) 1 year ago
  slaren 06bf2cf8c4 make : fix debug build with CUDA (#5616) 1 year ago
  Haoxiang Fei 8dbbd75754 metal : add build system support for embedded metal library (#5604) 1 year ago
  Jared Van Bortel f24ed14ee0 make : pass CPPFLAGS directly to nvcc, not via -Xcompiler (#5598) 1 year ago
  Georgi Gerganov d0e3ce51f4 ci : enable -Werror for CUDA builds (#5579) 1 year ago
  Georgi Gerganov 68a6b98b3c make : fix CUDA build (#5580) 1 year ago
  Xuan Son Nguyen 11b12de39b llama : add llama_chat_apply_template() (#5538) 1 year ago
  Jared Van Bortel a0c2dad9d4 build : pass all warning flags to nvcc via -Xcompiler (#5570) 1 year ago
  Ananta Bastola 6e4e973b26 ci : add an option to fail on compile warning (#3952) 1 year ago
  Johannes Gäßler ad014bba97 make: add error message for bad CUDA version (#5444) 1 year ago
  Johannes Gäßler 098f6d737b make: Use ccache for faster compilation (#5318) 1 year ago
  Johannes Gäßler 3c0d25c475 make: add nvcc info print (#5310) 1 year ago
  Johannes Gäßler 3cc5ed353c make: fix nvcc optimization flags for host code (#5309) 1 year ago
  0cc4m e920ed393d Vulkan Intel Fixes, Optimizations and Debugging Flags (#5301) 1 year ago
  Ali Nehzat d71ac90985 make : generate .a library for static linking (#5205) 1 year ago
  0cc4m 2307523d32 ggml : add Vulkan backend (#2059) 2 years ago
  Xuan Son Nguyen 48c857aa10 server : refactored the task processing logic (#5065) 2 years ago
  crasm 413e7b0559 ci : add model tests + script wrapper (#4586) 2 years ago
  Georgi Gerganov c918fe8dca metal : create autorelease pool during library build (#4970) 2 years ago
  Georgi Gerganov 4be5ef556d metal : remove old API (#4919) 2 years ago
  Kawrakow 326b418b59 Importance Matrix calculation (#4861) 2 years ago