Commit Graph

  • 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
  • bcc4e631cb Merge pull request #163 from abetlen/dependabot/pip/black-23.3.0 Andrei 2023-05-06 17:10:30 -04:00
  • aa203a0d65 Added mirostat sampling to the high level API. Maximilian Winter 2023-05-06 22:47:47 +02:00
  • fd80ddf703 Fix a bug with wrong type Mug 2023-05-06 22:22:28 +02:00
  • 996f63e9e1 Add utf8 to chat example Mug 2023-05-06 15:16:58 +02:00
  • 3ceb47b597 Fix mirastat requiring c_float Mug 2023-05-06 13:35:50 +02:00
  • 9797394c81 Wrong logit_bias parsed type Mug 2023-05-06 13:27:52 +02:00
  • 1895c11033 Rename postfix to suffix to match upstream Mug 2023-05-06 13:18:25 +02:00
  • c9bb602b26 Bump black from 23.1.0 to 23.3.0 dependabot[bot] 2023-05-05 23:25:53 +00:00
  • 2f2ea00a3d Merge pull request #160 from th-neu/main Andrei 2023-05-05 19:24:53 -04:00
  • 79d50a29f4 Create dependabot.yml Thomas Neu 2023-05-06 01:02:59 +02:00
  • 980903df93 Merge branch 'main' of github.com:abetlen/llama_cpp_python into main Andrei Betlen 2023-05-05 15:07:26 -04:00
  • 98bbd1c6a8 Fix eval logits type Andrei Betlen 2023-05-05 14:23:14 -04:00
  • b5f3e74627 Add return type annotations for embeddings and logits Andrei Betlen 2023-05-05 14:22:55 -04:00
  • 3e28e0e50c Fix: runtime type errors Andrei Betlen 2023-05-05 14:12:26 -04:00
  • e24c3d7447 Prefer explicit imports Andrei Betlen 2023-05-05 14:05:31 -04:00
  • 40501435c1 Fix: types Andrei Betlen 2023-05-05 14:04:12 -04:00
  • 66e28eb548 Fix temperature bug Andrei Betlen 2023-05-05 14:00:41 -04:00
  • 6702d2abfd Fix candidates type Andrei Betlen 2023-05-05 14:00:30 -04:00
  • 5e7ddfc3d6 Fix llama_cpp types Andrei Betlen 2023-05-05 13:54:22 -04:00
  • f712a04f4e Merge pull request #157 from th-neu/th-neu-readme-windows Andrei 2023-05-05 12:40:45 -04:00
  • 22c3056b2a Update README.md Thomas Neu 2023-05-05 18:40:00 +02:00
  • b6a9a0b6ba Add types for all low-level api functions Andrei Betlen 2023-05-05 12:22:27 -04:00
  • 5be0efa5f8 Cache should raise KeyError when key is missing Andrei Betlen 2023-05-05 12:21:49 -04:00
  • 24fc38754b Add cli options to server. Closes #37 Andrei Betlen 2023-05-05 12:08:28 -04:00
  • eb54e30f34 Update README.md Thomas Neu 2023-05-05 14:22:41 +02:00
  • 952ba9ecaf Update README.md Thomas Neu 2023-05-05 14:21:57 +02:00
  • 5f583b0179 Merge branch 'main' of github.com:abetlen/llama_cpp_python into main v0.1.43 Andrei Betlen 2023-05-04 21:59:40 -04:00
  • 5c165a85da Bump version Andrei Betlen 2023-05-04 21:59:37 -04:00
  • 853dc711cc Format Andrei Betlen 2023-05-04 21:58:36 -04:00
  • 97c6372350 Rewind model to longest prefix. Andrei Betlen 2023-05-04 21:58:27 -04:00
  • 38b8eeea58 Merge pull request #154 from th-neu/th-neu-dockerfile-slim Andrei 2023-05-04 19:59:23 -04:00
  • 5672ed7fea Merge branch 'abetlen:main' into th-neu-dockerfile-slim Thomas Neu 2023-05-04 21:41:13 +02:00
  • 501321875f Slim-Bullseye based docker image Thomas Neu 2023-05-04 21:03:19 +02:00
  • 0e9f227afd Update low level examples Mug 2023-05-04 18:33:08 +02:00
  • cabd8b8ed1 Bump version v0.1.42 Andrei Betlen 2023-05-04 12:21:20 -04:00
  • d78cec67df Update llama.cpp Andrei Betlen 2023-05-04 12:20:25 -04:00
  • 329297fafb Bugfix: Missing logits_to_logprobs Andrei Betlen 2023-05-04 12:18:40 -04:00
  • d594892fd4 Remove Docker CUDA build job Andrei Betlen 2023-05-04 00:02:46 -04:00
  • 0607f6578e Use network installer for cuda Andrei Betlen 2023-05-03 23:22:16 -04:00
  • 6d3c20e39d Add CUDA docker image build to github actions Andrei Betlen 2023-05-03 22:20:53 -04:00
  • 3008a954c1 Merge branch 'main' of github.com:abetlen/llama-cpp-python into better-server-params-and-fields Lucas Doyle 2023-05-03 13:10:03 -07:00
  • a02aa121da Remove cuda build job Andrei Betlen 2023-05-03 10:50:48 -04:00
  • 07a56dd9c2 Update job name Andrei Betlen 2023-05-03 10:39:39 -04:00
  • 7839eb14d3 Add docker cuda image. Closes #143 Andrei Betlen 2023-05-03 10:29:05 -04:00
  • 9e5b6d675a Improve logging messages Andrei Betlen 2023-05-03 10:28:10 -04:00
  • 43f2907e3a Support smaller state sizes Andrei Betlen 2023-05-03 09:33:50 -04:00
  • 1d47cce222 Update llama.cpp Andrei Betlen 2023-05-03 09:33:30 -04:00
  • b9098b0ef7 llama_cpp server: prompt is a string Lucas Doyle 2023-05-02 14:08:51 -07:00
  • 0fcc25cdac examples fastapi_server: deprecate Lucas Doyle 2023-04-28 23:54:31 -07:00
  • c2e31eecee Update permissions Andrei Betlen 2023-05-02 01:23:17 -04:00
  • 63f8d3a6fb Update context Andrei Betlen 2023-05-02 01:16:44 -04:00
  • c21a34506e Update permsissions Andrei Betlen 2023-05-02 01:13:43 -04:00
  • 872b2ec33f Clone submodules Andrei Betlen 2023-05-02 01:11:34 -04:00
  • 62de4692f2 Fix missing dependency Andrei Betlen 2023-05-02 01:09:27 -04:00
  • 25062cecd3 Merge pull request #140 from abetlen/Niek/main Andrei 2023-05-02 01:06:00 -04:00
  • 36c81489e7 Remove docker section of publish Andrei Betlen 2023-05-02 01:04:36 -04:00
  • 5d5421b29d Add build docker Andrei Betlen 2023-05-02 01:04:02 -04:00
  • 81631afc48 Install from local directory Andrei Betlen 2023-05-02 00:55:51 -04:00
  • d605408f99 Add dockerignore Andrei Betlen 2023-05-02 00:55:34 -04:00
  • e644e75915 Merge pull request #139 from matthoffner/patch-1 Andrei 2023-05-02 00:33:45 -04:00
  • f97ff3c5bb Update llama_cpp.py Matt Hoffner 2023-05-01 20:40:06 -07:00
  • e9e0654aed Bump version v0.1.41 Andrei Betlen 2023-05-01 22:52:25 -04:00
  • 7ab08b8d10 Merge branch 'main' into better-server-params-and-fields Andrei 2023-05-01 22:45:57 -04:00
  • 46e3c4b84a Fix Andrei Betlen 2023-05-01 22:41:54 -04:00
  • 9eafc4c49a Refactor server to use factory Andrei Betlen 2023-05-01 22:38:46 -04:00
  • dd9ad1c759 Formatting Andrei Betlen 2023-05-01 21:51:16 -04:00
  • dbbfc4ba2f llama_cpp server: fix to ChatCompletionRequestMessage Lucas Doyle 2023-05-01 11:48:37 -07:00
  • fa2a61e065 llama_cpp server: fields for the embedding endpoint Lucas Doyle 2023-04-29 18:46:01 -07:00
  • 8dcbf65a45 llama_cpp server: define fields for chat completions Lucas Doyle 2023-04-29 18:37:43 -07:00
  • 978b6daf93 llama_cpp server: add some more information to fields for completions Lucas Doyle 2023-04-29 14:37:36 -07:00
  • a5aa6c1478 llama_cpp server: add missing top_k param to CreateChatCompletionRequest Lucas Doyle 2023-04-29 11:52:20 -07:00
  • 1e42913599 llama_cpp server: move logprobs to supported Lucas Doyle 2023-04-29 11:48:49 -07:00
  • b47b9549d5 llama_cpp server: delete some ignored / unused parameters Lucas Doyle 2023-04-29 01:19:30 -07:00
  • e40fcb0575 llama_cpp server: mark model as required Lucas Doyle 2023-04-29 00:47:35 -07:00
  • 9d60ae56f2 Fix whitespace Andrei Betlen 2023-05-01 18:07:45 -04:00
  • 53c0129eb6 Update submoduele clone instructions Andrei Betlen 2023-05-01 18:07:15 -04:00
  • b6747f722e Fix logprob calculation. Fixes #134 Andrei Betlen 2023-05-01 17:45:08 -04:00
  • c088a2b3a7 Un-skip tests v0.1.40 Andrei Betlen 2023-05-01 15:46:03 -04:00
  • bf3d0dcb2c Fix tests Andrei Betlen 2023-05-01 15:28:46 -04:00
  • 5034bbf499 Bump version Andrei Betlen 2023-05-01 15:23:59 -04:00
  • f073ef0571 Update llama.cpp Andrei Betlen 2023-05-01 15:23:01 -04:00
  • 9ff9cdd7fc Fix import error Andrei Betlen 2023-05-01 15:11:15 -04:00
  • 2f8a3adaa4 Temporarily skip sampling tests. Andrei Betlen 2023-05-01 15:01:49 -04:00
  • dbe0ad86c8 Update test dependencies Andrei Betlen 2023-05-01 14:50:01 -04:00
  • 350a1769e1 Update sampling api Andrei Betlen 2023-05-01 14:47:55 -04:00
  • 7837c3fdc7 Fix return types and import comments Andrei Betlen 2023-05-01 14:02:06 -04:00
  • 55d6308537 Fix test dependencies Andrei Betlen 2023-05-01 11:39:18 -04:00
  • ccf1ed54ae Merge branch 'main' of github.com:abetlen/llama_cpp_python into main Andrei Betlen 2023-05-01 11:35:14 -04:00
  • 79ba9ed98d Merge pull request #125 from Stonelinks/app-server-module-importable Andrei 2023-05-01 11:31:08 -04:00
  • 80184a286c Update llama.cpp Andrei Betlen 2023-05-01 10:44:28 -04:00
  • efe8e6f879 llama_cpp server: slight refactor to init_llama function Lucas Doyle 2023-04-28 23:47:36 -07:00
  • 6d8db9d017 tests: simple test for server module Lucas Doyle 2023-04-28 23:26:07 -07:00
  • 468377b0e2 llama_cpp server: app is now importable, still runnable as a module Lucas Doyle 2023-04-28 22:43:37 -07:00
  • 755f9fa455 Merge pull request #118 from SagsMug/main Andrei 2023-04-29 07:19:01 -04:00
  • 18a0c10032 Remove excessive errors="ignore" and add utf8 test Mug 2023-04-29 12:19:22 +02:00
  • 523825e91d Update README Andrei Betlen 2023-04-28 17:12:03 -04:00