vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Commit graph

  • 0bc1e806d1 fix docker.yml Bernat Vadell 2023-03-16 12:02:22 +01:00
  • 4941df7f3b fix github action docker Bernat Vadell 2023-03-16 12:00:05 +01:00
  • c6b2c6fd8f include docker versioned images Bernat Vadell 2023-03-16 11:44:00 +01:00
  • c20281924c fix name runs-on macOS-latest is macos-latest (lowercase) Bernat Vadell 2023-03-16 11:43:49 +01:00
  • 3bcfc2b83d change CI to publish at github docker registry Bernat Vadell 2023-03-16 11:31:49 +01:00
  • 60cf70725e Merge branch 'master' into feat/dockerize Bernat Vadell 2023-03-16 11:23:07 +01:00
  • 2e2f144bcd
         Update README.md Geraint Ballinger 2023-03-16 09:07:10 +00:00
  • ac15de7895
         Expand "Contributing" section Georgi Gerganov 2023-03-16 08:55:13 +02:00
  • fcafaf03b0
         Add files via upload Black-Engineer 2023-03-16 08:23:02 +02:00
  • 273abc47ff
         Update hot topics - RMSnorm Georgi Gerganov 2023-03-16 07:12:12 +02:00
  • 610719ecc8
         Merge branch 'ggerganov:master' into fix-cmake-pthread mmyjona 2023-03-16 10:25:05 +08:00
  • 7b051e3fb0
         add cmake to linux and macos platform mmyjona 2023-03-16 10:23:09 +08:00
  • e13991e7cc Fix non-vectorised q4_1 vec mul Matvey Soloviev 2023-03-16 00:36:49 +01:00
  • edbd4a0534 Fix ggml_vec_mad_q4_1 too Matvey Soloviev 2023-03-16 00:23:42 +01:00
  • a2e9d4951b Rearrange Q4_1 quantization to work for multipart models. (Fix #152) Matvey Soloviev 2023-03-15 23:54:46 +01:00
  • ad051ac56e Small optimisations to q4_1 dot product (@Const-me) Matvey Soloviev 2023-03-15 01:29:36 +01:00
  • 561733cafa Add AVX2 version of ggml_vec_dot_q4_1 Matvey Soloviev 2023-03-14 19:37:58 +01:00
  • 9b4a15b17d
         Fix RMS norm in GGML (#191) Nebula 2023-03-15 19:29:25 -04:00
  • fa2aa1728a
         Fix RMS norm in GGML nebulatgs 2023-03-15 19:04:08 -04:00
  • 68e421da89
         Grammar improvements and more information glencoe2004 2023-03-15 18:54:50 -04:00
  • 599b3ca1e7
         Add files via upload glencoe2004 2023-03-15 18:53:24 -04:00
  • 6eac39ba95
         Add RMS norm and use it (#187) hoangmit 2023-03-15 18:41:38 -04:00
  • 11e594884b
         update op num hoangmit 2023-03-15 18:29:32 -04:00
  • a8f75ec41e
         add ggml_rms_norm hoangmit 2023-03-15 18:26:19 -04:00
  • d70f1fc72f
         Add files via upload glencoe2004 2023-03-15 18:23:48 -04:00
  • 11b3dafd2c
         Made the file clearer for future python versions Reelix 2023-03-15 23:36:55 +02:00
  • ae43513b39
         Added install instructions for latest python3 Reelix 2023-03-15 23:32:01 +02:00
  • 5f0ada21bf fix Dmitry Wolf 2023-03-16 00:30:07 +03:00
  • b430c51f99 Add --ignore-eos parameter Slaren 2023-03-15 22:14:09 +01:00
  • 27944c4206
         fixed typo (#178) moritzbrantner 2023-03-15 21:35:25 +01:00
  • bb034e5f78
         fixed typo moritzbrantner 2023-03-15 21:29:56 +01:00
  • de17acac72 readme Dmitry Wolf 2023-03-15 23:24:48 +03:00
  • c758d3d521 Merge branch 'master' into streaming Dmitry Wolf 2023-03-15 23:19:52 +03:00
  • 0deb075a3f clean Dmitry Wolf 2023-03-15 22:57:59 +03:00
  • 2d15d6c9a9
         add SIGINT support for _WIN32 environments (#120) Rickey Bowers Jr 2023-03-15 13:56:24 -06:00
  • 2d64715ad4
         added ctx_size parameter (#148) Justin Suess 2023-03-15 15:42:40 -04:00
  • 16b2c61a22
         fixed color reset on exit (#149) Justin Suess 2023-03-15 15:39:38 -04:00
  • 977295c700
         Fix potential licensing issue (#126) Musab Gultekin 2023-03-15 22:39:06 +03:00
  • bb997650be separate threads for r/w ops Dmitry Wolf 2023-03-15 22:38:28 +03:00
  • 956dfda8ad
         Use tokenizer.vocab_size() instead of hardcoding 32000 in convert-pth-to-ggml.py (#142) Ronsor 2023-03-15 12:37:50 -07:00
  • b4e2723a67
         Update main.cpp Georgi Gerganov 2023-03-15 21:36:58 +02:00
  • f056beb384
         Apply suggestions from code review Georgi Gerganov 2023-03-15 21:35:48 +02:00
  • 113e685d18
         inline -> static inline for "bytesFromNibbles" (#161) hoangmit 2023-03-15 15:05:14 -04:00
  • 289637a6a3 streaming conversion without pytorch Dmitry Wolf 2023-03-15 21:25:01 +03:00
  • b1a4a2a02a
         Update main.cpp Anujsharma002 2023-03-15 23:10:29 +05:30
  • 44f74671cb add docker action pipeline Bernat Vadell 2023-03-15 17:45:33 +01:00
  • 279400845b
         CMake: properly find and link to threading library Gleb Popov 2023-03-15 19:36:16 +03:00
  • 405d94e61f
         inline -> static inline for "bytesFromNibbles" hoangmit 2023-03-15 11:08:54 -04:00
  • 2788f373be
         Get the build working Justine Tunney 2023-03-15 02:52:31 -07:00
  • 1b73521840 Use F16 for memory_k and memory_v Ty Everett 2023-03-14 23:10:12 -07:00
  • a4fb5a9719 fixed warning with std::ignore about unused function result Justin 2023-03-15 02:37:01 +00:00
  • 9eb4598fa3 added it in more places Justin 2023-03-15 02:33:56 +00:00
  • 1ddaee93fb added sigint handler for ansi_color_reset Justin 2023-03-15 01:56:14 +00:00
  • e3d780d833 added ctx_size parameter Justin 2023-03-15 01:47:51 +00:00
  • cb5234aeea
         Added magnet link to download model files Jonathan Mackenzie 2023-03-15 12:25:51 +11:00
  • 116f94bfa2 fixed color reset on exit Justin 2023-03-15 01:23:55 +00:00
  • c3c89050c3
         Merge branch 'ggerganov:master' into master apaz 2023-03-15 00:34:40 +00:00
  • 3878230201 Resolved merge conflicts. apaz-cli 2023-03-14 18:42:12 -05:00
  • 6894b63556 Added mmap() iostream implementation. apaz-cli 2023-03-14 18:32:51 -05:00
  • f89ca6fd36 Set executable bit Danil Yarantev (Yardanico) 2023-03-15 00:11:07 +03:00
  • f781b1904d Fix line endings in quantize.sh from CRLF to LF Danil Yarantev (Yardanico) 2023-03-15 00:10:02 +03:00
  • 9da4e66710
         Use tokenizer.vocab_size() instead of hardcoding 32000 in convert-pth-to-ggml.py Ronsor 2023-03-14 13:33:41 -07:00
  • 84fb7f516c Nix: fix ARM neon dotproduct on macOS Niklas Korz 2023-03-14 21:14:29 +01:00
  • a296589180 Remove direnv Niklas Korz 2023-03-14 18:34:25 +01:00
  • 0759896135 Nix: remove channel compatibility Niklas Korz 2023-03-14 18:33:53 +01:00
  • 1171c0e663 Nix: use python packages supplied by withPackages Niklas Korz 2023-03-14 13:29:03 +01:00
  • 3ee54ef522 direnv: use flake instead of use_flake Niklas Korz 2023-03-13 12:01:57 +01:00
  • a9230b679b Nix: development shel, direnv and compatibility Niklas Korz 2023-03-13 10:48:39 +01:00
  • 034b589102 Nix: only add Accelerate framework on macOS Niklas Korz 2023-03-13 10:23:53 +01:00
  • 8defc0a54e Nix flake Niklas Korz 2023-03-12 10:15:46 +01:00
  • e1b1e12a41 modularize qunash 2023-03-14 22:52:22 +03:00
  • 901c34d1b1
         Update .devops/tools.sh Bernat Vadell 2023-03-14 20:46:41 +01:00
  • 47857e564c
         Don't use vdotq_s32 if it's not available (#139) Ronsor 2023-03-14 12:34:37 -07:00
  • fcbadc6f59
         Update ggml.c Georgi Gerganov 2023-03-14 21:34:12 +02:00
  • 777aa4e53d
         Don't use vdotq_s32 if it's not available Ronsor 2023-03-14 10:53:41 -07:00
  • 297863982c Change subtext according to ggerganov recommendations Leszek Hanusz 2023-03-14 18:19:45 +01:00
  • a4590d3be9 add quantize into tool docker image Bernat Vadell 2023-03-14 18:04:21 +01:00
  • ae380dddbf Forgot to regenerate the pdf with the lowercase a in llama Leszek Hanusz 2023-03-14 16:35:07 +01:00
  • 5fc3112110 Adding llama banner in README.md Leszek Hanusz 2023-03-14 16:14:25 +01:00
  • 9959b1f374 split dockerfile into main & tools Bernat Vadell 2023-03-14 15:46:03 +01:00
  • 6d9ad1058b feat: split build & runtime stages Bernat Vadell 2023-03-14 15:03:25 +01:00
  • 60f819a2b1
         Add section to README on how to run the project on Android (#130) Radoslav Gerganov 2023-03-14 15:30:08 +02:00
  • 23fe89d2e9 Add section to README on how to run the project on Android Radoslav Gerganov 2023-03-14 14:43:32 +02:00
  • ce509c79c5 feat: dockerize llamacpp Bernat Vadell 2023-03-14 14:16:52 +01:00
  • 311fc3fca2
         Functionality addition CMakeLists.txt nusu-github 2023-03-14 19:51:08 +09:00
  • 8e1210f993
         Update README.md Musab Gultekin 2023-03-14 13:19:33 +03:00
  • c81a58190c
         Update README.md Musab Gultekin 2023-03-14 13:10:39 +03:00
  • 5e539c06a8 Fix build for Android Radoslav Gerganov 2023-03-14 10:59:06 +02:00
  • 97ab2b2578
         Add Misc section + update hot topics + minor fixes Georgi Gerganov 2023-03-14 09:43:52 +02:00
  • 585431924a perhaps more consistent Rickey Bowers Jr 2023-03-14 00:43:11 -06:00
  • 570e4ff810 add SIGINT support for _WIN32 environments Rickey Bowers Jr 2023-03-14 00:39:22 -06:00
  • 68897eb13a Use STL in input processing and fix off-by-one bug Thomas Antony 2023-03-13 21:07:49 -07:00
  • fdb1987f6f
         add ptread link to fix cmake build under linux mmyjona 2023-03-14 12:19:45 +08:00
  • c2af31149f Refactoring: more concise and readable qunash 2023-03-14 03:57:35 +03:00
  • d8aba05a62 Use f-strings instead of concatenation qunash 2023-03-14 01:55:51 +03:00
  • 94f368fd53 Refactor get_n_parts function to simplify code and improve readability qunash 2023-03-14 01:50:50 +03:00
  • 2f700a2738
         Add windows to the CI (#98) Sebastián A 2023-03-13 17:29:10 -03:00
  • c09a9cfb06
         CMake build in Release by default (#75) Georgi Gerganov 2023-03-13 21:22:15 +02:00
  • b5ae4eb92d Add windows to the CI Sebastián Aedo 2023-03-13 15:31:15 -03:00
  • 7ec903d3c1
         Update contribution section, hot topics, limitations, etc. Georgi Gerganov 2023-03-13 19:21:51 +02:00