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

Commit graph

  • 4497ad819c
         Print system information Georgi Gerganov 2023-03-13 19:15:08 +02:00
  • ed6849cc07
         Initial support for CMake (#75) Sebastián A 2023-03-13 14:12:33 -03:00
  • 41be0a3b3d
         Add NetBSD support. (#90) Thomas Klausner 2023-03-13 17:40:54 +01:00
  • 671d5cac15
         Use fprintf for diagnostic output (#48) Pavol Rusnak 2023-03-13 17:39:56 +01:00
  • 84d9015c4a
         Use vdotq_s32 to improve performance (#67) Georgi Gerganov 2023-03-13 18:36:44 +02:00
  • 0fa481b092
         Back to original change Georgi Gerganov 2023-03-13 18:35:42 +02:00
  • 63fd76fbb0
         Reduce model loading time (#43) uint256_t 2023-03-14 01:33:43 +09:00
  • 3419f88f11
         Minor Georgi Gerganov 2023-03-13 18:33:23 +02:00
  • 2a20f48efa
         Fix UTF-8 handling (including colors) (#79) Val Kharitonov 2023-03-13 12:24:18 -04:00
  • d1f224712d
         Add quantize script for batch quantization (#92) Pavol Rusnak 2023-03-13 17:15:20 +01:00
  • acf35ec45a
         Fix file list on Mac OS Georgi Gerganov 2023-03-13 18:14:22 +02:00
  • 23d334b660
         Fix script name Georgi Gerganov 2023-03-13 18:09:18 +02:00
  • 5f5332b4ef
         README for new quantize.sh Georgi Gerganov 2023-03-13 18:08:14 +02:00
  • d328973aa1
         Indentation Georgi Gerganov 2023-03-13 18:05:18 +02:00
  • bc2b35ec69
         Updating README after running 60B of llama.cpp Joshua Herman 2023-03-13 09:43:34 -05:00
  • a1eff53587 remove unused header wizard 2023-03-13 22:42:12 +08:00
  • daedf7ce97
         Add quantize script for batch quantization Pavol Rusnak 2023-03-13 13:49:46 +01:00
  • 6d9c32e94a Initial support for CMake Sebastián Aedo 2023-03-12 23:17:55 -03:00
  • fa8ce2a207 Add NetBSD support. Thomas Klausner 2023-03-13 12:25:28 +01:00
  • 6b9e424671 add support to load tokenizer.model from command line argument wizard 2023-03-13 18:01:05 +08:00
  • 7438b83939
         Merge branch 'ggerganov:master' into master wizd 2023-03-13 17:03:31 +08:00
  • ed10def70e clean code wizard 2023-03-13 17:02:06 +08:00
  • 15f06f6b4f buffering utf-8 output to make it complete for spliting output. wizard 2023-03-13 16:27:11 +08:00
  • 1808ee0500
         Add initial contribution guidelines Georgi Gerganov 2023-03-13 09:42:26 +02:00
  • 6c8258665b
         use fprintf for diagnostic output Pavol Rusnak 2023-03-13 08:25:02 +01:00
  • 9ec1dfdbe2 Strip trailing whitespace from prompt file Matthew McAllister 2023-03-12 22:13:23 -07:00
  • 86e967c54b buffering output for UTF-8 encoded token wizard 2023-03-13 13:06:01 +08:00
  • cb8c464a60 Fix UTF-8 handling (including colors) Valery Kharitonov 2023-03-13 01:01:34 -04:00
  • 1133eea479 Truncate prompt if longer than context + n_predict Matthew McAllister 2023-03-12 21:49:17 -07:00
  • b8f20713b9
         Add __pycache__ and *.bin to gitignore Jed Fox 2023-03-12 22:21:22 -04:00
  • 34af8a97e8
         FIx parsing single-byte UTF-8 tokens by manually parsing the protobuf Jed Fox 2023-03-12 20:16:05 -04:00
  • a169bb889c Gate signal support on being on a unixoid system. (#74) dev Matvey Soloviev 2023-03-13 04:08:01 +01:00
  • 9b4077184a introduces justfile Barton Rhodes 2023-03-13 02:37:04 +00:00
  • 1b87fe1e90 call a standalone function to untokenize output wizard 2023-03-13 10:00:34 +08:00
  • 307dba3dd2 first try to intergrate sentencepiece wizard 2023-03-13 10:00:01 +08:00
  • ce7ebb3319
         Another antiprompt fix beiller 2023-03-08 16:44:50 -05:00
  • 9425a21db5
         Bugfix and back to printing as normal Fix antiprompt beiller 2023-03-08 16:44:50 -05:00
  • efaa30ef11
         Use vector maekawatoshiki 2023-03-13 10:38:41 +09:00
  • 703571861f
         undo complicated printing until its fixed sadly beiller 2023-03-08 16:44:50 -05:00
  • 5ed9219221
         Update convert-pth-to-ggml.py Dietrich Daroch 2023-03-12 17:45:55 -07:00
  • bb40590714 Misc: Use argparse Dietrich Daroch 2023-03-12 17:18:59 -07:00
  • 81c9c9e8a6 Misc: Make the conversion script executable Dietrich Daroch 2023-03-12 17:05:13 -07:00
  • 460c482540 Fix token count accounting Matvey Soloviev 2023-03-13 00:35:51 +01:00
  • ee36313770
         Ah -std=c++17 is needed beiller 2023-03-08 16:44:50 -05:00
  • 07771aab81
         ensure cmake is proper version beiller 2023-03-08 16:44:50 -05:00
  • 3e2327c96a
         Try manually adding CXX flag beiller 2023-03-08 16:44:50 -05:00
  • 3c04dfb436
         run build in shell beiller 2023-03-08 16:44:50 -05:00
  • 7deae8a2ca
         fix build procedure beiller 2023-03-08 16:44:50 -05:00
  • 67b1c842d9
         Use sentencepiece tokenization beiller 2023-03-08 16:44:50 -05:00
  • 96dc6a0c68
         work towards tokenizer integration beiller 2023-03-08 16:44:50 -05:00
  • 0ac8651bd6
         10% performance boost on ARM Georgi Gerganov 2023-03-13 01:30:53 +02:00
  • c80e2a8f2a
         Revert "10% performance boost on ARM" Georgi Gerganov 2023-03-13 01:28:08 +02:00
  • 54a0e66ea0
         Check for vdotq_s32 availability Georgi Gerganov 2023-03-13 01:21:03 +02:00
  • 543c57e991
         Ammend to previous commit - forgot to update non-QRDMX branch Georgi Gerganov 2023-03-13 01:05:24 +02:00
  • 113a9e83eb
         10% performance boost on ARM Georgi Gerganov 2023-03-13 00:56:10 +02:00
  • 404fac0d62
         Fix color getting reset before prompt output done (#65) Matvey Soloviev 2023-03-12 23:07:34 +01:00
  • ea840344b3 Fix color getting reset before prompt output done Matvey Soloviev 2023-03-12 22:50:21 +01:00
  • 1a0a74300f
         Update README.md Georgi Gerganov 2023-03-12 23:39:01 +02:00
  • 96ea727f47
         Add interactive mode (#61) Matvey Soloviev 2023-03-12 22:13:28 +01:00
  • 0453507450 Fix OS X build Matvey Soloviev 2023-03-12 21:59:32 +01:00
  • f47face9a5
         Update README to explain interactive mode. Matvey Soloviev 2023-03-12 21:56:45 +01:00
  • 798428465c Improve interactive mode. Make rev. prompt optional. Matvey Soloviev 2023-03-12 21:09:04 +01:00
  • 81d09b2101 Initial work on interactive mode. Matvey Soloviev 2023-03-12 20:20:45 +01:00
  • 9661954835
         Fix typo in README (#45) Marc Köhlbrugge 2023-03-13 03:30:08 +07:00
  • f385f8dee8
         Allow using prompt files (#59) Ben Garney 2023-03-12 13:28:36 -07:00
  • 63a8b00d88 fix: older standard for compatibility valentynbez 2023-03-12 21:27:22 +01:00
  • 02f0c6fe7f
         Add back top_k (#56) beiller 2023-03-12 16:23:15 -04:00
  • 90b9b5b8c0
         Update utils.h Georgi Gerganov 2023-03-12 22:22:56 +02:00
  • 2913d75a42
         Update utils.cpp Georgi Gerganov 2023-03-12 22:22:37 +02:00
  • eb062bb012
         Windows fixes (#31) Sebastián A 2023-03-12 17:15:00 -03:00
  • 7027a97837
         Update README.md Georgi Gerganov 2023-03-12 22:09:26 +02:00
  • 2d555e5b42
         Add CI (#60) Georgi Gerganov 2023-03-12 22:08:24 +02:00
  • 2a3d4c8c7e
         Add CI Georgi Gerganov 2023-03-12 22:06:19 +02:00
  • 25c1d0a291
         Update utils.cpp Ben Garney 2023-03-12 12:58:05 -07:00
  • 7c9e54e55e
         Revert "weights_only" arg - this causing more trouble than help Georgi Gerganov 2023-03-12 20:59:01 +02:00
  • 7412189fe5
         Add back top_k Bill Hamilton 2023-03-08 16:44:50 -05:00
  • 3b20e78c16 Change the use of vector for stack allocations. Sebastián Aedo 2023-03-12 12:39:57 -03:00
  • 526ddc0101 fix: add POSIX functionality for Linux compilation valentynbez 2023-03-12 15:42:25 +01:00
  • b577e34c1d
         Add osx-specific python install instructions John Albietz 2023-03-12 09:00:34 -04:00
  • b9bd1d0141
         python/pytorch compat notes (#44) Oleksandr Nikitin 2023-03-12 14:16:33 +02:00
  • 2fed42d9d4
         Fix typo in README Marc Köhlbrugge 2023-03-12 18:10:24 +07:00
  • 97a25c1460
         python/pytorch compat notes Oleksandr Nikitin 2023-03-12 12:52:41 +02:00
  • 640fd77a25 Use buffering maekawatoshiki 2023-03-12 19:38:25 +09:00
  • 129c7d1ea8
         Add repetition penalty (#20) beiller 2023-03-12 05:27:42 -04:00
  • ebb357f711
         Minor formatting Georgi Gerganov 2023-03-12 11:26:48 +02:00
  • 702fddf5c5
         Clarify meaning of hacking Georgi Gerganov 2023-03-12 09:03:25 +02:00
  • c2201a9a83 Add comment. Jay Krell 2023-03-11 22:55:17 -08:00
  • bea4af5c9c Fix sizeof(pp). Jay Krell 2023-03-11 22:45:08 -08:00
  • 7d86e25bf6
         README: add "Supported platforms" + update hot topics Georgi Gerganov 2023-03-12 08:41:54 +02:00
  • a93120236f
         use weights_only in conversion script (#32) deepdiffuser 2023-03-11 22:36:35 -08:00
  • 3225d9b8a0 nologo Jay Krell 2023-03-11 22:36:05 -08:00
  • 6a9a67f0be
         Add LICENSE (#21) Pavol Rusnak 2023-03-12 07:36:03 +01:00
  • ec64cfa1db define NDEBUG, and simplify casts. Jay Krell 2023-03-11 22:34:06 -08:00
  • a05225f194 LTCG and Win32 is Win32, not specific compilers. Jay Krell 2023-03-11 22:27:38 -08:00
  • 636d56818a Port to Visual C++. Jay Krell 2023-03-11 22:00:20 -08:00
  • c505a2d217 Fix zero initialization of the other fields. Sebastián Aedo 2023-03-12 02:12:53 -03:00
  • 1ed5c7c75b use weights_only in conversion script deepdiffuser 2023-03-11 20:09:28 -08:00
  • ce0d5fb9de MSVC: Remove features that are only available on MSVC C++20. Sebastián Aedo 2023-03-12 00:11:08 -03:00
  • 718bb989a5 Remove unsupported VLAs Sebastián Aedo 2023-03-12 00:02:03 -03:00
  • 2d29d4b89e Apply fixes suggested to build on windows Sebastián Aedo 2023-03-11 19:26:20 -03:00