Cronologia Commit

Autore SHA1 Messaggio Data
  CRD716 a8a2efdc81 examples : various prompt and example fixes (#1298) 2 anni fa
  Evan Jones e216aa0463 llama : only copy used KV cache in get / set state (#1272) 2 anni fa
  DannyDaemonic 2485d7a4d3 Process escape sequences given in prompts (#1173) 2 anni fa
  DannyDaemonic 13b0c68ed7 Handle signals properly on Windows (#1123) 2 anni fa
  DannyDaemonic 55bc5f0900 Call sh on build-info.sh (#1294) 2 anni fa
  kuvaus 9daff419f6 fix build-info.h for git submodules (#1289) 2 anni fa
  slaren bf4b22ffe4 fix missing parameters in `llama_init_from_gpt_params` (#1293) 2 anni fa
  Ron Evans 67c77799e0 examples : add llama_init_from_gpt_params() common function (#1290) 2 anni fa
  Georgi Gerganov 0e6cbff1b7 llama : fix compile warnings 2 anni fa
  Georgi Gerganov 5d5817ca60 ggml : fix 32-bit ARM 2 anni fa
  Ron Evans 8c9be35ff9 examples : improve vertical alignment of a few variables (#1286) 2 anni fa
  Marvin Gießing cc0bb7235c ggml : fix ppc64le build error and make cmake detect Power processors (#1284) 2 anni fa
  Robert Brisita 2bb992f034 llama : allow 0 as a seed number. (#1275) 2 anni fa
  Ron Evans e2cd506999 main : switch input_noecho to input_echo to remove negation (#979) 2 anni fa
  slaren 2d099e5193 ggml: add names to tensors (#1268) 2 anni fa
  DannyDaemonic f4cef87edf Add git-based build information for better issue tracking (#1232) 2 anni fa
  slaren 58b367c2d7 cuBLAS: refactor and optimize f16 mat mul performance (#1259) 2 anni fa
  xloem ea3a0ad6b6 llama : update stubs for systems without mmap and mlock (#1266) 2 anni fa
  Kerfuffle 2bdc09646d ggml : fix ggml_used_mem() (#1264) 2 anni fa
  Georgi Gerganov 70269cae37 llama : fix session load / save (#1263) 2 anni fa
  slaren b925f1f1b0 cuBLAS: fall back to pageable memory if pinned alloc fails (#1233) 2 anni fa
  Alex Klinkhamer 90b19bd6ee llama : let context be const when accessing const data (#1261) 2 anni fa
  Georgi Gerganov 7ff0dcd320 ggml : fix UB (int << 31) 2 anni fa
  Pavol Rusnak 6f79699286 build: add armv{6,7,8} support to cmake (#1251) 2 anni fa
  jon-chuang a5d30b1f53 common : better default number of threads (#934) 2 anni fa
  0cc4m 76a884920a ggml : add CLBlast q5_0, q5_1, q8_0 dequant kernels (#1225) 2 anni fa
  Georgi Gerganov 6bc4400e67 ggml : add Q5 WASM SIMD + GGML_FTYPE 2 anni fa
  Stephan Walter f0d70f147d Various fixes to mat_mul benchmark (#1253) 2 anni fa
  Georgi Gerganov 3e5aa8a1c4 ggml : fix labels for GGML_OP_ALIBI 2 anni fa
  Georgi Gerganov c3ca7a5f05 ggml : fix 32-bit ARM NEON 2 anni fa