Commit Graph

  • 88184ed217 fix CJK output again MeouSker77 2023-08-09 22:04:35 +08:00
  • 66fb0345e8 Move grammar to function call argument Andrei Betlen 2023-08-08 15:08:54 -04:00
  • 1e844d3238 fix Andrei Betlen 2023-08-08 15:07:28 -04:00
  • 843b7ccd90 Merge branch 'main' into c0sogi/main Andrei Betlen 2023-08-08 14:43:02 -04:00
  • bf0c603c51 Merge branch 'main' into fix-on-m1 Andrei Betlen 2023-08-08 14:38:35 -04:00
  • 36041c8bec Merge branch 'main' of github.com:abetlen/llama_cpp_python into main Andrei Betlen 2023-08-08 14:35:10 -04:00
  • d015bdb4f8 Add mul_mat_q option Andrei Betlen 2023-08-08 14:35:06 -04:00
  • dcc26f7f78 Merge pull request #573 from mzen17/spelling-error-patch Andrei 2023-08-08 14:32:34 -04:00
  • f6a7850e1a Update llama.cpp Andrei Betlen 2023-08-08 14:30:58 -04:00
  • 1dd4774ca9 Merge pull request #583 from abetlen/dependabot/pip/mkdocs-1.5.2 Andrei 2023-08-08 14:24:40 -04:00
  • 03e575f6a5 Merge pull request #584 from abetlen/dependabot/pip/fastapi-0.101.0 Andrei 2023-08-08 14:24:31 -04:00
  • 83f8438c4f Bump fastapi from 0.100.1 to 0.101.0 dependabot[bot] 2023-08-07 20:10:12 +00:00
  • 4cf2fc7d3d Bump mkdocs from 1.5.1 to 1.5.2 dependabot[bot] 2023-08-07 20:09:55 +00:00
  • 0d7d2031a9 prevent memory access error by llama_grammar_free c0sogi 2023-08-07 17:02:33 +09:00
  • b07713cb9f reset grammar for every generation c0sogi 2023-08-07 15:16:25 +09:00
  • 418aa83b01 Added grammar based sampling c0sogi 2023-08-07 02:21:37 +09:00
  • 097fba25e5 Fixed spelling error "lowe-level API" to "low-level API" Mike Zeng 2023-08-05 02:00:04 -05:00
  • ac188a21f3 Added low level grammar API c0sogi 2023-08-05 14:43:35 +09:00
  • 9f499af6b0 Update llama.cpp bretello 2023-08-03 18:23:26 +02:00
  • 39978ccaf5 add mul_mat_q parameter bretello 2023-08-03 18:22:52 +02:00
  • a5bc57e279 Update README.md Ihsan Soydemir 2023-08-03 16:49:45 +02:00
  • d4844b93ae Merge pull request #2 from Isydmr/isydmr/docker-improvements Ihsan Soydemir 2023-08-03 16:42:27 +02:00
  • cdab73536b Docker improvements Ihsan Soydemir 2023-08-03 16:36:50 +02:00
  • 60e85cbe46 Fix dev setup in README.md so that everyone can run it Huge 2023-08-02 12:27:08 +02:00
  • 91bf8fac1b Merge pull request #550 from abetlen/dependabot/pip/uvicorn-0.23.2 Andrei 2023-08-01 17:39:25 -04:00
  • 0cc8d8282a Bump uvicorn from 0.23.1 to 0.23.2 dependabot[bot] 2023-08-01 21:25:18 +00:00
  • 5011ef4fc6 Merge pull request #549 from abetlen/dependabot/pip/mkdocs-material-9.1.21 Andrei 2023-08-01 17:24:04 -04:00
  • 7fb4f0bda2 Merge pull request #548 from abetlen/dependabot/pip/fastapi-0.100.1 Andrei 2023-08-01 17:23:45 -04:00
  • ecb72cc0a2 Bump mkdocs-material from 9.1.19 to 9.1.21 dependabot[bot] 2023-07-31 20:32:04 +00:00
  • 4a2f41a803 Bump fastapi from 0.100.0 to 0.100.1 dependabot[bot] 2023-07-31 20:31:16 +00:00
  • ce57920e60 Suppress llama.cpp output when loading model. Andrei Betlen 2023-07-28 14:45:18 -04:00
  • a9b9f0397c Format Andrei Betlen 2023-07-28 01:53:08 -04:00
  • abc538fcd5 fix: annoying bug where attribute exceptions were droining out file not found exceptions Andrei Betlen 2023-07-28 01:43:00 -04:00
  • d89bf8c072 Merge pull request #536 from Isydmr/patch-2 Andrei 2023-07-28 01:37:23 -04:00
  • 3e77eea7ec Fix OpenBLAS Docker build Ihsan Soydemir 2023-07-27 19:44:15 +02:00
  • ffa81218f6 Merge pull request #531 from abetlen/dependabot/pip/uvicorn-0.23.1 Andrei 2023-07-26 23:46:57 -04:00
  • 583d63351a Bump uvicorn from 0.22.0 to 0.23.1 dependabot[bot] 2023-07-27 03:33:07 +00:00
  • 468fccbed7 Merge pull request #532 from abetlen/dependabot/pip/black-23.7.0 Andrei 2023-07-26 23:31:48 -04:00
  • ecdfe4fbd3 Bump black from 23.3.0 to 23.7.0 dependabot[bot] 2023-07-26 19:08:28 +00:00
  • 6e6c275c94 Merge pull request #530 from abetlen/dependabot/pip/mkdocs-material-9.1.19 Andrei 2023-07-26 15:07:21 -04:00
  • bfbbc8db14 Bump mkdocs-material from 9.1.18 to 9.1.19 dependabot[bot] 2023-07-26 17:54:39 +00:00
  • 7debb505ab Merge pull request #516 from charles-dyfis-net/poetry-no-versions-in-extras Andrei 2023-07-26 13:53:48 -04:00
  • e665b557fd Merge pull request #523 from shouyiwang/tensor_split Andrei 2023-07-26 13:53:02 -04:00
  • d3bf7db2db Merge pull request #525 from Isydmr/patch-1 Andrei 2023-07-25 16:31:02 -04:00
  • 0687a3092b Fix typo in 70B path Ihsan Soydemir 2023-07-25 20:49:44 +02:00
  • 426dbfe3f4 Change tensor_split from array to pointer Shouyi Wang 2023-07-25 18:29:59 +10:00
  • 078902a6fe Add llama_grammar_accept_token Andrei Betlen 2023-07-24 15:55:26 -04:00
  • bf901773b0 Add llama_sample_grammar Andrei Betlen 2023-07-24 15:42:31 -04:00
  • 1b6997d69f Convert constants to python types and allow python types in low-level api Andrei Betlen 2023-07-24 15:42:07 -04:00
  • 343480364f Merge branch 'main' into v0.2-wip Andrei Betlen 2023-07-24 15:26:08 -04:00
  • c7c700b0d4 Bump version v0.1.77 Andrei Betlen 2023-07-24 14:11:21 -04:00
  • 11dd2bf382 Add temporary rms_norm_eps parameter Andrei Betlen 2023-07-24 14:09:24 -04:00
  • 8cd64d4ac3 Add rms_eps_norm Andrei Betlen 2023-07-24 13:52:12 -04:00
  • e4431a6ade Merge pull request #522 from bretello/llama2-70b-support Andrei 2023-07-24 13:48:26 -04:00
  • 0f09f10e8c add support for llama2 70b bretello 2023-07-24 15:51:19 +02:00
  • 77c9f496b0 Merge branch 'main' into v0.2-wip Andrei Betlen 2023-07-24 13:19:54 -04:00
  • 4aaaec561d Bump version v0.1.76 Andrei Betlen 2023-07-24 13:12:38 -04:00
  • 401309d11c Revert "Merge pull request #521 from bretello/main" Andrei Betlen 2023-07-24 13:11:10 -04:00
  • 07f0f3a386 Merge pull request #521 from bretello/main Andrei 2023-07-24 13:09:28 -04:00
  • d8a3ddbb1c Update llama.cpp Andrei Betlen 2023-07-24 13:08:06 -04:00
  • 985d559971 Update llama.cpp Andrei Betlen 2023-07-24 13:04:34 -04:00
  • 8be7d67f7e raise exception when llama_load_model_from_file fails bretello 2023-07-24 14:42:37 +02:00
  • c03fa87956 pyproject.toml: extras list should contain only package list, not versions (#515) Charles Duffy 2023-07-23 13:15:40 -05:00
  • 436036aa67 Merge branch 'main' into v0.2-wip Andrei Betlen 2023-07-21 12:42:38 -04:00
  • 231123ee1e Update llama.cpp v0.1.75 Andrei Betlen 2023-07-21 12:41:59 -04:00
  • b83728ad1e Update llama.cpp Andrei Betlen 2023-07-21 12:33:27 -04:00
  • 0538ba1dab Merge branch 'main' into v0.2-wip Andrei Betlen 2023-07-20 19:06:26 -04:00
  • a4fe3fe350 Bump version v0.1.74 Andrei Betlen 2023-07-20 18:56:29 -04:00
  • 01435da740 Update llama.cpp Andrei Betlen 2023-07-20 18:54:25 -04:00
  • 28a111704b Fix compatibility with older python versions Andrei Betlen 2023-07-20 18:52:10 -04:00
  • d10ce62714 Revert ctypes argtype change Andrei Betlen 2023-07-20 18:51:53 -04:00
  • 365d9a4367 Merge pull request #481 from c0sogi/main Andrei 2023-07-20 17:41:42 -04:00
  • a9cb645495 Merge pull request #511 from viniciusarruda/patch-1 Andrei 2023-07-20 17:40:39 -04:00
  • a8551477f5 Update llama_cpp.py - Fix c_char_p to Array[c_char_p] and c_float to Array[c_float] Vinicius 2023-07-20 17:29:11 -03:00
  • 5549a1cabd Merge pull request #508 from ctejada85/main Andrei 2023-07-20 16:07:54 -04:00
  • 0756a2d3fb Now the last token sent when stream=True Carlos Tejada 2023-07-19 22:47:14 -04:00
  • 0b121a7456 Format Andrei Betlen 2023-07-19 03:48:27 -04:00
  • b43917c144 Add functions parameters Andrei Betlen 2023-07-19 03:48:20 -04:00
  • 36872620d0 Merge pull request #501 from a10y/patch-1 Andrei 2023-07-18 22:26:42 -04:00
  • b6b2071180 Update install instructions for Linux OpenBLAS Andrew Duffy 2023-07-18 22:22:33 -04:00
  • 57db1f9570 Update development docs for scikit-build-core. Closes #490 Andrei Betlen 2023-07-18 20:26:25 -04:00
  • d2c5afe5a3 Remove prerelease python version Andrei Betlen 2023-07-18 19:38:51 -04:00
  • 7ce6cdf45b Update supported python versions. Andrei Betlen 2023-07-18 19:37:52 -04:00
  • 792b981119 Fix numpy dependency Andrei Betlen 2023-07-18 19:30:06 -04:00
  • 19ba9d3845 Use numpy arrays for logits_processors and stopping_criteria. Closes #491 Andrei Betlen 2023-07-18 19:27:41 -04:00
  • 5eab1db0d0 Merge branch 'main' into v0.2-wip Andrei 2023-07-18 18:54:27 -04:00
  • a05cfaf815 Merge pull request #498 from ctejada85/windows-pip-install Andrei 2023-07-18 18:53:24 -04:00
  • 6cb77a20c6 Migrate to scikit-build-core. Closes #489 Andrei Betlen 2023-07-18 18:52:29 -04:00
  • b24b10effd Added info to set ENV variables in PowerShell Carlos Tejada 2023-07-18 17:14:42 -04:00
  • c9985abc03 Bump version v0.1.73 Andrei Betlen 2023-07-18 13:54:51 -04:00
  • 9127bc2777 Update llama.cpp Andrei Betlen 2023-07-18 13:54:42 -04:00
  • 071ac799d5 Merge pull request #485 from callMeMakerRen/main Andrei 2023-07-18 12:30:21 -04:00
  • 5ed8bf132f expose RoPE param to server start shutup 2023-07-18 16:34:36 +08:00
  • 1551ba10bd Added RouteErrorHandler for server c0sogi 2023-07-16 14:57:39 +09:00
  • 6d8892fe64 Bump version v0.1.72 Andrei Betlen 2023-07-15 17:13:55 -04:00
  • 8ab098e49d Re-order Llama class params Andrei Betlen 2023-07-15 15:35:08 -04:00
  • e4f9db37db Fix context_params struct layout Andrei Betlen 2023-07-15 15:34:55 -04:00
  • bdf32df255 Add additional direnv directory to gitignore Andrei Betlen 2023-07-15 15:34:32 -04:00
  • d0572f4fca Merge branch 'custom_rope' into main Andrei Betlen 2023-07-15 15:11:43 -04:00
  • f0797a6054 Merge branch main into custom_rope Andrei Betlen 2023-07-15 15:11:01 -04:00