Revīziju vēsture

Autors SHA1 Ziņojums Datums
  Georgi Gerganov 0f07cacb05 ggml : fix q4_1 dot product types 2 gadi atpakaļ
  Howard Su c5d70f5c9e ggml : optimize rope function to avoid call powf in the tight loop (#807) 2 gadi atpakaļ
  Gary Linscott be87b6ed20 perplexity : add support for batch size to `--perplexity` (#407) 2 gadi atpakaļ
  CRD716 0e07e6a839 common : remove unnecessary includes (#947) 2 gadi atpakaļ
  Georgi Gerganov a3a2a0eda8 ggml : add GGML_DEFAULT_N_THREADS 2 gadi atpakaļ
  Georgi Gerganov d990e3fffc ggml : speed-up ggml_vec_dot_q4_1() ARM_NEON + 32-bit ARM support (#900) 2 gadi atpakaļ
  Georgi Gerganov 9190e8eac8 llama : merge llama_internal.h into llama.h 2 gadi atpakaļ
  Georgi Gerganov c85980acd0 gitignore : benchmark 2 gadi atpakaļ
  Stephan Walter 6232f2d7fd ggml : optimize non-SIMD Q4_0 vector dot product (#703) 2 gadi atpakaļ
  Pavol Rusnak 6c248707f5 ggml : introduce GGML_ALIGNED_MALLOC/GGML_ALIGNED_FREE macros (#884) 2 gadi atpakaļ
  CRD716 8cda5c981d fix whitespace (#944) 2 gadi atpakaļ
  CRD716 ec29272175 readme : remove python 3.10 warning (#929) 2 gadi atpakaļ
  Genkagaku.GPT 7e941b95eb readme : llama node binding (#911) 2 gadi atpakaļ
  Pavol Rusnak c729ff730a flake.nix: add all binaries from bin (#848) 2 gadi atpakaļ
  Judd 4579af95e8 zig : update build.zig (#872) 2 gadi atpakaļ
  Vladimir 8c3ffc2f04 ggml : update cblas_sgemm columns var to be more reasonable (#838) 2 gadi atpakaļ
  niansa/tuxifan 107980d970 examples : add -n to alpaca and gpt4all scripts (#706) 2 gadi atpakaļ
  anzz1 585d91a156 cmake : add explicit F16C option (x86) (#576) 2 gadi atpakaļ
  SebastianApel 95ea26f6e9 benchmark : add tool for timing q4_0 matrix multiplication (#653) 2 gadi atpakaļ
  Pavol Rusnak 82d146df9b do not force the prompt file to end with a new line (#908) 2 gadi atpakaļ
  Stephan Walter e7f6997f89 Don't crash on ftype (formerly f16) == 4 (#917) 2 gadi atpakaļ
  Georgi Gerganov f76cb3a34d readme : change "GPU support" link to discussion 2 gadi atpakaļ
  Georgi Gerganov 782438070f readme : update hot topics with link to "GPU support" issue 2 gadi atpakaļ
  Nicolai Weitkemper 4dbbd40750 readme: link to sha256sums file (#902) 2 gadi atpakaļ
  Pavol Rusnak 8b679987cd Fix whitespace, add .editorconfig, add GitHub workflow (#883) 2 gadi atpakaļ
  Stephan Walter 3e6e70d8e8 Add enum llama_ftype, sync ggml_type to model files (#709) 2 gadi atpakaļ
  comex 2663d2c678 Windows fixes (#890) 2 gadi atpakaļ
  qouoq a0caa34b16 Add BAIR's Koala to supported models (#877) 2 gadi atpakaļ
  Georgi Gerganov 461ba9e66e ggml : fix WASM build 2 gadi atpakaļ
  Georgi Gerganov c3ac702e5e ggml : add ggml_cont() + optimize ggml_cpy() for contiguous dst 2 gadi atpakaļ