Commit Graph

  • 5f15a3d91c Disable wheel repair command Andrei Betlen 2023-11-10 06:05:42 -05:00
  • e02d52df29 Try to clean before calling cibuildwheel Andrei Betlen 2023-11-10 06:01:58 -05:00
  • ed5a9260f6 Force LD_LIBRARY_PATH Andrei Betlen 2023-11-10 05:54:23 -05:00
  • 2f070afd61 Don't install in editable mode for release Andrei Betlen 2023-11-10 05:45:44 -05:00
  • e32ecb0516 Fix tests Andrei Betlen 2023-11-10 05:39:42 -05:00
  • 6f0b0b1b84 Fix sampling bug when logits_all=False Andrei Betlen 2023-11-10 05:15:41 -05:00
  • d9b38e3e3a Potential bugfix for eval Andrei Betlen 2023-11-10 04:41:19 -05:00
  • 52350cc9d7 Merge branch 'main' of https://github.com/abetlen/llama-cpp-python into main Andrei Betlen 2023-11-10 04:24:51 -05:00
  • b84d76a844 Fix: add default stop sequence to chatml chat format Andrei Betlen 2023-11-10 04:24:48 -05:00
  • 841f6167cc Add Code Completion section to docs Andrei Betlen 2023-11-10 04:06:14 -05:00
  • 1b376c62b7 Update functionary for new OpenAI API Andrei Betlen 2023-11-10 02:51:58 -05:00
  • 17da8fb446 Add missing tool_calls finish_reason Andrei Betlen 2023-11-10 02:51:06 -05:00
  • 770df34436 Add $ref and $defs support to json schema converter Andrei Betlen 2023-11-10 02:50:46 -05:00
  • faeae181b1 Fix: json_schema_to_gbnf should take string dump of json schema as input Andrei Betlen 2023-11-10 02:50:17 -05:00
  • e7962d2c73 Fix: default max_tokens matches openai api (16 for completion, max length for chat completion) Andrei Betlen 2023-11-10 02:49:27 -05:00
  • 82072802ea Add link to bakllava gguf model Andrei Betlen 2023-11-09 03:05:18 -05:00
  • baeb7b34b3 Merge branch 'main' of github.com:abetlen/llama_cpp_python into main Andrei Betlen 2023-11-09 00:55:25 -05:00
  • b62c449839 Bugfix: missing response_format for functionary and llava chat handlers Andrei Betlen 2023-11-09 00:55:23 -05:00
  • fb1f956a27 Fix server doc arguments (#892) Kevin Jung 2023-11-08 23:53:00 -05:00
  • 80f4162bf4 Update llama.cpp Andrei Betlen 2023-11-08 11:18:15 -05:00
  • fd41ed3a90 Add set_seed to Llama class Andrei Betlen 2023-11-08 11:09:41 -05:00
  • ca4cb88351 Fix destructor NoneType is not callable error Andrei Betlen 2023-11-08 11:05:45 -05:00
  • 01cb3a0381 Bump version v0.2.15 Andrei Betlen 2023-11-08 00:54:54 -05:00
  • 9ae9c86be0 Update server docs Andrei Betlen 2023-11-08 00:52:13 -05:00
  • 598780fde8 Update Multimodal notebook Andrei Betlen 2023-11-08 00:48:25 -05:00
  • b30b9c338b Add JSON mode support. Closes #881 Andrei Betlen 2023-11-08 00:07:16 -05:00
  • 4852a6a39c Fix built in GBNF grammar rules Andrei Betlen 2023-11-08 00:06:22 -05:00
  • 64f5153c35 Add seed parameter to chat handlers Andrei Betlen 2023-11-07 23:41:29 -05:00
  • 86aeb9f3a1 Add seed parameter support for completion and chat_completion requests. Closes #884 Andrei Betlen 2023-11-07 23:37:28 -05:00
  • da1b80285a Update changelog Andrei Betlen 2023-11-07 23:15:26 -05:00
  • 9a8e64d29d Update llama.cpp Andrei Betlen 2023-11-07 23:14:19 -05:00
  • 3660230faa Fix docs multi-modal docs Andrei Betlen 2023-11-07 22:52:08 -05:00
  • aab74f0b2b Multimodal Support (Llava 1.5) (#821) Damian Stewart 2023-11-08 04:48:51 +01:00
  • 56171cf7bf Bump version v0.2.14 Andrei Betlen 2023-11-06 09:37:55 -05:00
  • 52320c348c Add python 3.12 classifier Andrei Betlen 2023-11-06 09:34:07 -05:00
  • 4286830f16 Add python3.12 tests Andrei Betlen 2023-11-06 09:32:20 -05:00
  • be0add1b2d Fix type bug Andrei Betlen 2023-11-06 09:30:38 -05:00
  • e214a58422 Refactor Llama class internals Andrei Betlen 2023-11-06 09:16:36 -05:00
  • bbffdaebaa Refactor autotokenizer format to reusable function Andrei Betlen 2023-11-06 09:07:27 -05:00
  • b0e597e46e Pin python version in release Andrei Betlen 2023-11-06 08:56:41 -05:00
  • 4ff8def4d0 #717: Add support for Huggingface Autotokenizer (#790) Joe 2023-11-05 17:06:36 -06:00
  • 3580e2c5df Update llama_chat_format.py (#869) earonesty 2023-11-05 17:00:13 -05:00
  • f0b30ef7dc Update llama.cpp Andrei Betlen 2023-11-05 16:57:10 -05:00
  • dccbac82eb Update llama.cpp Andrei Betlen 2023-11-03 18:12:22 -04:00
  • 2ec043af76 Clean up stdout / stderr suppression Andrei Betlen 2023-11-03 13:02:15 -04:00
  • 4ea7027c41 Rename internal only module utils to _utils Andrei Betlen 2023-11-03 12:55:55 -04:00
  • df9362eeea Update llama.cpp Andrei Betlen 2023-11-03 11:34:50 -04:00
  • 3af7b21ff1 Add functionary support (#784) Andrei 2023-11-03 02:12:14 -04:00
  • df31303a12 Update CHANGELOG Andrei Betlen 2023-11-02 20:16:32 -04:00
  • ab028cb878 Migrate inference to llama_batch and llama_decode api (#795) Andrei 2023-11-02 20:13:57 -04:00
  • f436e0c872 Update llama.cpp Andrei Betlen 2023-11-02 17:34:01 -04:00
  • 8350de9a18 Bump version v0.2.13 Andrei Betlen 2023-11-02 15:53:01 -04:00
  • 9ffe62d665 Update llama.cpp Andrei Betlen 2023-11-02 15:45:27 -04:00
  • 011b95d7f3 Fix name 'open' is not defined exception. Closes #860 Andrei Betlen 2023-11-02 15:30:55 -04:00
  • fa83cc5f9c Update llama.cpp Andrei Betlen 2023-11-02 13:40:20 -04:00
  • ddbd10c442 Fix clblast test Andrei Betlen 2023-11-02 01:17:46 -04:00
  • 735522272b Fix runner label Andrei Betlen 2023-11-01 22:17:53 -04:00
  • 0feffb9c20 Cleanup Andrei Betlen 2023-11-01 21:37:53 -04:00
  • 7fe0bd3a31 Update CHANGELOG Andrei Betlen 2023-11-01 21:31:54 -04:00
  • 4d4e0f11e2 fix: tokenization of special characters: (#850) Antoine Lizee 2023-11-02 01:29:06 +00:00
  • 952e4cc3ce Fix: use linux image for opencl test Andrei Betlen 2023-11-01 21:31:02 -04:00
  • 8bf7fa6e5f Add opencl test Andrei Betlen 2023-11-01 21:18:36 -04:00
  • 446d5f5649 Add metal ci test Andrei Betlen 2023-11-01 21:15:01 -04:00
  • c89eadafbf Update CHANGELOG Andrei Betlen 2023-11-01 19:40:04 -04:00
  • 6b3aa7fc8f Bump version v0.2.12 Andrei Betlen 2023-11-01 19:25:03 -04:00
  • 3fbcded7cd Add missing n_seq_id to llama_batch (#842) NickAlgra 2023-11-01 23:56:29 +01:00
  • 7b136bb5b1 Fix for shared library not found and compile issues in Windows (#848) Sujeendran Menon 2023-11-02 04:25:57 +05:30
  • eefd76fe81 llama: fix exception in Llama.__del__ (#846) cebtenzzre 2023-11-01 18:53:57 -04:00
  • 3fc9147218 Iterate over tokens that should be biased rather than the entire vocabulary. (#851) David Ponce 2023-11-01 23:53:47 +01:00
  • 9c8f4dca5f fixed Llama._create_completion suffix check, it can be either None or str instance (#854) Marko Tasic 2023-11-01 23:52:50 +01:00
  • 5f8f369d1b Pass-Through grammar parameter in web server. (#855) Closes #778 Daniel Thuerck 2023-11-01 23:51:12 +01:00
  • 25cb710281 Update llama_types.py (#849) Adam Katora 2023-11-01 18:50:11 -04:00
  • bdf5254658 Update llama.cpp Andrei Betlen 2023-11-01 14:15:56 -04:00
  • d808fd436c Update llama.cpp Andrei Betlen 2023-10-31 21:29:35 -04:00
  • 53861c9e53 Update llama.cpp Andrei Betlen 2023-10-24 03:13:32 -04:00
  • acf50f179a Update llama.cpp Andrei Betlen 2023-10-20 11:17:31 -04:00
  • 5a045fcbbc Update llama.cpp Andrei Betlen 2023-10-19 17:37:07 -04:00
  • ef03d77b59 Enable finish reason tests Andrei Betlen 2023-10-19 02:56:45 -04:00
  • 09a8406c83 Fix streaming doesn't return finish reason (#798) gmcgoldr 2023-10-19 02:55:56 -04:00
  • 28c2b884e2 Merge branch 'main' of github.com:abetlen/llama_cpp_python into main Andrei Betlen 2023-10-19 02:55:31 -04:00
  • cbeef36510 Re-enable tests completion function Andrei Betlen 2023-10-19 02:55:29 -04:00
  • ff580031d2 Update llama.cpp Andrei Betlen 2023-10-19 02:55:08 -04:00
  • a315128d66 update value check for n_gpu_layers field (#826) Xiaoyu Kevin Hu 2023-10-18 17:25:25 -05:00
  • d989ac86e6 Update llama.cpp Andrei Betlen 2023-10-15 15:12:57 -04:00
  • 10304d75fc Make use of suppress_stdout_stderr when freeing model (#803) Pierre Alexandre SCHEMBRI 2023-10-15 19:52:43 +02:00
  • a1ac199980 Fix repeat greeting (#808) Ma, Guokai 2023-10-16 01:52:21 +08:00
  • b50166500e Add validation for tensor_split size exceeding LLAMA_MAX_DEVICES (#820) Eric Liu 2023-10-15 10:51:51 -07:00
  • f30aa20126 Update llama.cpp Andrei Betlen 2023-10-12 02:24:50 -04:00
  • 622bff19b2 Update llama.cpp Andrei Betlen 2023-10-10 19:23:35 -04:00
  • d6a130a052 Print traceback on server error Andrei Betlen 2023-10-10 15:56:04 -04:00
  • 43dfe1e2ab Update llama.cpp Andrei Betlen 2023-10-05 16:07:49 -04:00
  • 2c0456acf0 Update llama.cpp Andrei Betlen 2023-10-04 20:19:31 -04:00
  • c305be6db6 Merge branch 'main' of github.com:abetlen/llama_cpp_python into main Andrei Betlen 2023-10-03 15:23:37 -04:00
  • a7d17b8ac9 Update llama.cpp Andrei Betlen 2023-10-03 15:23:35 -04:00
  • b76724cddc Update instruction to download GGUF model (#783) ccshen 2023-10-02 23:46:47 +08:00
  • 305482bd41 Add chatml chat format Andrei Betlen 2023-09-30 21:01:34 -04:00
  • 5ef5280ef9 Log server exceptions to stdout Andrei Betlen 2023-09-30 19:13:36 -04:00
  • f0af1c7201 Update llama.cpp Andrei Betlen 2023-09-30 19:09:50 -04:00
  • fab4bccc35 Bump version v0.2.11 Andrei Betlen 2023-09-30 16:04:46 -04:00
  • d696251fbe Fix logits_all bug Andrei Betlen 2023-09-30 16:02:35 -04:00