Commit History

Author SHA1 Message Date
  Georgi Gerganov 8c00b7a6ff sync : ggml (Metal F32 support + reduce ggml-alloc size) (#3192) 2 years ago
  Georgi Gerganov a51b687657 metal : relax conditions on fast matrix multiplication kernel (#3168) 2 years ago
  Eric Sommerlade b52b29ab9d arm64 support for windows (#3007) 2 years ago
  Georgi Gerganov b3e9852e47 sync : ggml (CUDA GLM RoPE + POSIX) (#3082) 2 years ago
  Przemysław Pawełczyk cb6c44c5e0 build : do not use _GNU_SOURCE gratuitously (#2035) 2 years ago
  Kunshang Ji 7f412dab9c enable CPU HBM (#2603) 2 years ago
  Cebtenzzre 00d62adb79 fix some warnings from gcc and clang-tidy (#3038) 2 years ago
  Przemysław Pawełczyk fec2fb19e4 ggml : posixify madvise and pagesize (#3037) 2 years ago
  Jhen-Jie Hong 21f3d1be86 k-quants : fix build on armv7 (android only) (#2920) 2 years ago
  Tameem 5aec2cfaac ggml : add RISC-V vector intrinsics support (#2929) 2 years ago
  slaren 06abf8eeba ggml : add view_src and view_offs to ggml_tensor for views (#2874) 2 years ago
  xaedes 44c117f41e train : mem usage and other improvements (#2439) 2 years ago
  Georgi Gerganov 35feac6560 ggml : sync (mem align to header + conv_transpose_2d fixes + ggml_alloc) (#2852) 2 years ago
  Georgi Gerganov f55538c3cc metal : fix memory leak (#2762) 2 years ago
  Georgi Gerganov 103cfafc77 gguf : fix strings to not be null-terminated (#2839) 2 years ago
  Georgi Gerganov d0cee0d36d gguf : add 64-bit support (GGUF v2) (#2821) 2 years ago
  Przemysław Pawełczyk 1591e2e590 ggml : detect SSSE3 (#2825) 2 years ago
  Georgi Gerganov cf658adc83 llm : add Falcon support (#2717) 2 years ago
  Georgi Gerganov ef3f333d37 ggml : sync latest (SAM + SD operators, CUDA alibi) (#2709) 2 years ago
  Georgi Gerganov 6381d4e110 gguf : new file format with flexible meta data (beta) (#2398) 2 years ago
  slaren 9e232f0234 ggml : move all type info to ggml_type_traits (#2663) 2 years ago
  Georgi Gerganov 93356bdb7a ggml : mul mat tweaks (#2372) 2 years ago
  Georgi Gerganov 60baff7c85 ggml : pad result of ggml_nbytes() 2 years ago
  Georgi Gerganov 9082b5dfbf ggml : change params pointer (style change) (#2539) 2 years ago
  Georgi Gerganov 99d29c0094 ggml : sync (custom ops) (#2537) 2 years ago
  slaren a113689571 ggml : add graph tensor allocator (#2411) 2 years ago
  slaren b5472ea0ad ggml : fix assert in ggml_set_unary_op (#2410) 2 years ago
  slaren 5488fb789e ggml : allocate graphs in a context (#2392) 2 years ago
  slaren 07aaa0f63f ggml : fix ggml_flash_attn to use op_params (#2387) 2 years ago
  Jiahao Li 875086bdb9 ggml : relax contiguous constraints in activation function (#2371) 2 years ago