Cronologia Commit

Autore SHA1 Messaggio Data
  Georgi Gerganov e128a1bf5b tests : fix test-quantize-fns to init the CPU backend (#12306) 10 mesi fa
  Georgi Gerganov f6d12e7df8 tests : fix compile warning 1 anno fa
  Diego Devesa ae8de6d50a ggml : build backends as libraries (#10256) 1 anno fa
  Diego Devesa 9f40989351 ggml : move CPU backend to a separate file (#10144) 1 anno fa
  Diego Devesa dca1d4b58a ggml : fix BLAS with unsupported types (#9775) 1 anno fa
  compilade 9bc6db28d0 ggml-quants : ternary packing for TriLMs and BitNet b1.58 (#8151) 1 anno fa
  Georgi Gerganov 370b1f7e7a ggml : minor naming changes (#8433) 1 anno fa
  Kawrakow 1f2fd4e727 tests : include IQ2_XXS and IQ2_XS in test-quantize-fns (#6303) 1 anno fa
  Kawrakow a33e6a0d2a Adding IQ2_S and IQ2_M to complete coverage of the 2-3 bit quantization range (#5721) 1 anno fa
  Kawrakow 4c4cb30736 IQ3_S: a much better alternative to Q3_K (#5676) 1 anno fa
  snadampal a07d0fee1f ggml : add mmla kernels for quantized GEMM (#4966) 1 anno fa
  Kawrakow f4d7e54974 SOTA 3-bit quants (#5196) 1 anno fa
  Kawrakow 49662cbed3 ggml : SOTA 2-bit quants (add IQ2_XS) (#4856) 2 anni fa
  Kawrakow dd5ae06405 SOTA 2-bit quants (#4773) 2 anni fa
  Georgi Gerganov 207b51900e ggml : move FP16 <-> FP32 code to ggml-impl.h (#3861) 2 anni fa
  Cebtenzzre 3aefaab9e5 check C++ code with -Wmissing-declarations (#3184) 2 anni fa
  Stephan Walter 1b107b8550 ggml : generalize `quantize_fns` for simpler FP16 handling (#1237) 2 anni fa
  Borislav Stanimirov 9cbf50c041 build : fix and ignore MSVC warnings (#1889) 2 anni fa
  Kawrakow 99009e72f8 ggml : add SOTA 2,3,4,5,6 bit k-quantizations (#1684) 2 anni fa
  Georgi Gerganov 7a32fcb3b2 ggml : add Q8_0 quantization format (rename the old one to Q8_1) (ARM NEON) (#1179) 2 anni fa
  Stephan Walter c50b628810 Fix CI: ARM NEON, quantization unit tests, editorconfig (#1122) 2 anni fa
  unbounded 5f939498d5 ggml : unit test for quantization functions (#953) 2 anni fa