Commit Graph

  • 6ece8a225a Set CUDA_VERSION as build ARG Marcel Coetzee 2023-05-18 16:59:42 +02:00
  • 6c57d38552 Decrement CUDA version and bump Ubuntu Marcel Coetzee 2023-05-18 16:02:42 +02:00
  • 50e136252a Update llama.cpp Andrei Betlen 2023-05-17 16:14:12 -04:00
  • db10e0078b Update docs Andrei Betlen 2023-05-17 16:14:01 -04:00
  • 61d58e7b35 Check for CUDA_PATH before adding Andrei Betlen 2023-05-17 15:26:38 -04:00
  • 7c95895626 Merge branch 'main' of github.com:abetlen/llama_cpp_python into main Andrei Betlen 2023-05-17 15:19:32 -04:00
  • 47921a312c Merge pull request #225 from aneeshjoy/main Andrei 2023-05-17 15:17:37 -04:00
  • e9794f91f2 Fixd CUBLAS dll load issue in Windows Aneesh Joy 2023-05-17 18:04:58 +01:00
  • 70695c430b Move docs link up Andrei Betlen 2023-05-17 11:40:12 -04:00
  • 4f342795e5 Update token checks Andrei Betlen 2023-05-17 03:35:13 -04:00
  • 626003c884 Merge branch 'main' of github.com:abetlen/llama_cpp_python into main Andrei Betlen 2023-05-17 02:00:48 -04:00
  • f5c2f998ab Format Andrei Betlen 2023-05-17 02:00:39 -04:00
  • d28b753ed2 Implement penalize_nl Andrei Betlen 2023-05-17 01:53:26 -04:00
  • f11e2a781c Fix last_n_tokens_size Andrei Betlen 2023-05-17 01:42:51 -04:00
  • 7e55244540 Fix top_k value. Closes #220 Andrei Betlen 2023-05-17 01:41:42 -04:00
  • e37a808bc0 Update llama.cpp Andrei Betlen 2023-05-16 23:33:53 -04:00
  • a7c9e38287 Update variable name Andrei Betlen 2023-05-16 18:07:25 -04:00
  • a3352923c7 Add model_alias option to override model_path in completions. Closes #39 Andrei Betlen 2023-05-16 17:22:00 -04:00
  • 214589e462 Update llama.cpp Andrei Betlen 2023-05-16 17:20:45 -04:00
  • a65125c0bd Add sampling defaults for generate Andrei Betlen 2023-05-16 09:35:50 -04:00
  • 341c50b5b0 Fix CMakeLists.txt Andrei Betlen 2023-05-16 09:07:14 -04:00
  • 1a13d76c48 Merge pull request #215 from zxybazh/main Andrei 2023-05-15 17:57:58 -04:00
  • 408dd14e5b Update README.md Xiyou Zhou 2023-05-15 14:52:25 -07:00
  • e0cca841bf Merge pull request #214 from abetlen/dependabot/pip/mkdocs-material-9.1.12 Andrei 2023-05-15 17:24:06 -04:00
  • 7526b3f6f9 Bump mkdocs-material from 9.1.11 to 9.1.12 dependabot[bot] 2023-05-15 21:05:54 +00:00
  • cda9cecd5f Merge pull request #212 from mzbac/patch-1 Andrei 2023-05-15 16:19:00 -04:00
  • cbac19bf24 Add winmode arg only on windows if python version supports it Andrei Betlen 2023-05-15 09:15:01 -04:00
  • 3718799b37 chore: add note for Mac m1 installation Anchen 2023-05-15 20:46:59 +10:00
  • c804efe3f0 Fix obscure Wndows DLL issue. Closes #208 Andrei Betlen 2023-05-14 22:08:11 -04:00
  • ceec21f1e9 Update llama.cpp Andrei Betlen 2023-05-14 22:07:35 -04:00
  • d90c9df326 Bump version v0.1.50 Andrei Betlen 2023-05-14 00:04:49 -04:00
  • cdf59768f5 Update llama.cpp Andrei Betlen 2023-05-14 00:04:22 -04:00
  • 7a536e86c2 Allow model to tokenize strings longer than context length and set add_bos. Closes #92 Andrei Betlen 2023-05-12 14:28:22 -04:00
  • 8740ddc58e Only support generating one prompt at a time. Andrei Betlen 2023-05-12 07:21:46 -04:00
  • 8895b9002a Revert "llama_cpp server: prompt is a string". Closes #187 Andrei Betlen 2023-05-12 07:16:57 -04:00
  • 684d7c8c17 Fix docker command Andrei Betlen 2023-05-11 22:12:35 -04:00
  • fa1fc4ec42 Merge branch 'main' of github.com:abetlen/llama_cpp_python into main v0.1.49 Andrei Betlen 2023-05-11 21:56:54 -04:00
  • e3d3c31da2 Bump version Andrei Betlen 2023-05-11 21:56:43 -04:00
  • 7be584fe82 Add missing tfs_z paramter Andrei Betlen 2023-05-11 21:56:19 -04:00
  • 28ee2adec2 Update llama.cpp Andrei Betlen 2023-05-11 21:15:12 -04:00
  • 35229f5eab Update llama.cpp Andrei Betlen 2023-05-11 10:05:34 -04:00
  • cdeaded251 Bugfix: Ensure logs are printed when streaming Andrei Betlen 2023-05-10 16:12:17 -04:00
  • c3ed1330d7 Merge pull request #177 from joelkurian/main Andrei 2023-05-10 05:27:12 -04:00
  • 3c96b43cf4 Merge pull request #178 from Stonelinks/document-presence-frequency-penalty Andrei 2023-05-09 23:55:52 -04:00
  • 02e8a018ae llama_cpp server: document presence_penalty and frequency_penalty, mark as supported Lucas Doyle 2023-05-09 16:19:46 -07:00
  • bebe7712f7 README: better setup instructions for developers for pip and poetry Lucas Doyle 2023-04-30 23:28:50 -07:00
  • 7e03fdd766 poetry: add poetry.toml, configure to install in a virtualenv Lucas Doyle 2023-04-30 23:22:54 -07:00
  • 99c016c9b3 pyproject.toml: add skbuild to dev dependencies Lucas Doyle 2023-04-30 23:21:16 -07:00
  • 17dc51a7d2 Updated installation instructions for BLAS backends Joel Kurian 2023-05-09 21:34:46 +05:30
  • d957422bf4 Implement sampling as in llama.cpp main example Andrei Betlen 2023-05-08 21:21:25 -04:00
  • 93a9019bb1 Merge branch 'main' of github.com:abetlen/llama_cpp_python into Maximilian-Winter/main Andrei Betlen 2023-05-08 19:57:09 -04:00
  • f315b82832 Revert changes to llama.cpp and setup.py Andrei Betlen 2023-05-08 19:53:21 -04:00
  • 7499fc1cbb Merge pull request #126 from Stonelinks/deprecate-example-server Andrei 2023-05-08 19:29:04 -04:00
  • 1971514fa5 Merge pull request #173 from abetlen/dependabot/pip/mkdocs-material-9.1.11 Andrei 2023-05-08 19:28:01 -04:00
  • 7af1f4c672 Merge branch 'main' of github.com:abetlen/llama_cpp_python into main v0.1.48 Andrei Betlen 2023-05-08 18:49:38 -04:00
  • c37883b477 Bump version Andrei Betlen 2023-05-08 18:49:37 -04:00
  • 82d138fe54 Fix: default repeat_penalty Andrei Betlen 2023-05-08 18:49:11 -04:00
  • b1489befda Bump mkdocs-material from 9.1.9 to 9.1.11 dependabot[bot] 2023-05-08 21:04:42 +00:00
  • ed0f48b4bb Merge pull request #153 from SagsMug/main Andrei 2023-05-08 14:58:47 -04:00
  • a3cc7bf5b2 Bump version v0.1.47 Andrei Betlen 2023-05-08 14:46:50 -04:00
  • 29f094bbcf Bugfix: not falling back to environment variables when default is value is set. Andrei Betlen 2023-05-08 14:46:25 -04:00
  • 6d69461ef5 Bump version v0.1.46 Andrei Betlen 2023-05-08 14:21:47 -04:00
  • 0d6c60097a Show default value when --help is called Andrei Betlen 2023-05-08 14:21:15 -04:00
  • 022e9ebcb8 Use environment variable if parsed cli arg is None Andrei Betlen 2023-05-08 14:20:53 -04:00
  • eaf9f19aa9 Fix lora Mug 2023-05-08 15:27:42 +02:00
  • 2c0d9b182c Fix session loading and saving in low level example chat Mug 2023-05-08 15:27:03 +02:00
  • ed66a469c9 Merge branch 'main' of https://github.com/abetlen/llama-cpp-python Mug 2023-05-08 14:49:48 +02:00
  • 0d751a69a7 Set repeat_penalty to 0 by default Andrei Betlen 2023-05-08 01:50:43 -04:00
  • 65d9cc050c Add openai frequency and presence penalty parameters. Closes #169 Andrei Betlen 2023-05-08 01:30:18 -04:00
  • 75d8619b1a Bump version v0.1.45 Andrei Betlen 2023-05-07 20:19:34 -04:00
  • a0b61ea2a7 Bugfix for models endpoint Andrei Betlen 2023-05-07 20:17:52 -04:00
  • e72f58614b Change pointer to lower overhead byref Andrei Betlen 2023-05-07 20:01:34 -04:00
  • 14da46f16e Added cache size to settins object. Andrei Betlen 2023-05-07 19:33:17 -04:00
  • 0e94a70de1 Add in-memory longest prefix cache. Closes #158 Andrei Betlen 2023-05-07 19:31:26 -04:00
  • 8dfde63255 Fix return type Andrei Betlen 2023-05-07 19:30:14 -04:00
  • 2753b85321 Format Andrei Betlen 2023-05-07 13:19:56 -04:00
  • 4f8cf52a38 Update README Andrei Betlen 2023-05-07 05:20:04 -04:00
  • 3adc8fb3ae Update README to use cli options for server Andrei Betlen 2023-05-07 05:10:52 -04:00
  • 627811ea83 Add verbose flag to server Andrei Betlen 2023-05-07 05:09:10 -04:00
  • 5f43c553d5 Bump version v0.1.44 Andrei Betlen 2023-05-07 03:29:33 -04:00
  • 3fbda71790 Fix mlock_supported and mmap_supported return type Andrei Betlen 2023-05-07 03:04:22 -04:00
  • 5a3413eee3 Update cpu_count Andrei Betlen 2023-05-07 03:03:57 -04:00
  • 1a00e452ea Update settings fields and defaults Andrei Betlen 2023-05-07 02:52:20 -04:00
  • 86753976c4 Revert "llama_cpp server: delete some ignored / unused parameters" Andrei Betlen 2023-05-07 02:02:34 -04:00
  • c382d8f86a Revert "llama_cpp server: mark model as required" Andrei Betlen 2023-05-07 02:00:22 -04:00
  • d8fddcce73 Merge branch 'main' of github.com:abetlen/llama_cpp_python into better-server-params-and-fields Andrei Betlen 2023-05-07 01:54:00 -04:00
  • 397ae97f64 Update README Andrei Betlen 2023-05-07 01:41:19 -04:00
  • 1c188459c4 Merge branch 'main' of github.com:abetlen/llama_cpp_python into main Andrei Betlen 2023-05-07 00:41:10 -04:00
  • 7c3743fe5f Update llama.cpp Andrei Betlen 2023-05-07 00:12:47 -04:00
  • c76e0913bb Update issue templates Andrei 2023-05-06 22:18:31 -04:00
  • bc853e3742 Fix type for eval_logits in LlamaState object Andrei Betlen 2023-05-06 21:32:50 -04:00
  • ec617c04c1 Merge pull request #164 from abetlen/dependabot/pip/mkdocstrings-0.21.2 Andrei 2023-05-06 21:30:09 -04:00
  • ae3c639764 Bump mkdocstrings from 0.20.0 to 0.21.2 dependabot[bot] 2023-05-07 00:16:31 +00:00
  • 8a692a5838 Merge pull request #161 from abetlen/dependabot/pip/pytest-7.3.1 Andrei 2023-05-06 20:15:35 -04:00
  • 33d41fb8f3 Bump pytest from 7.2.2 to 7.3.1 dependabot[bot] 2023-05-07 00:07:39 +00:00
  • c7becd9363 Merge pull request #162 from abetlen/dependabot/pip/mkdocs-1.4.3 Andrei 2023-05-06 20:06:14 -04:00
  • 515d9bde7e Fixed somethings and activated cublas Maximilian Winter 2023-05-06 23:40:19 +02:00
  • 2a21b8f69e Bump mkdocs from 1.4.2 to 1.4.3 dependabot[bot] 2023-05-06 21:16:08 +00:00
  • d077e641f9 Merge pull request #165 from abetlen/dependabot/pip/mkdocs-material-9.1.9 Andrei 2023-05-06 17:14:45 -04:00
  • fdcab2286c Bump mkdocs-material from 9.1.4 to 9.1.9 dependabot[bot] 2023-05-06 21:11:57 +00:00