Pull Requests abetlen/llama-cpp-python

Add timeout and error handling in FastAPI uvicorn server

#2044 opened 2025-07-22 10:46 by amandwivedi45

Actually create a random seed when using seed = -1 on load

#2042 opened 2025-07-16 09:00 by m-from-space

Improve error message when model file is missing

#2041 opened 2025-07-09 10:06 by NITHIN0710

ARM Runners support CUDA SBSA

#2039 opened 2025-07-07 10:45 by johnnynunez

Flush libc stdout/stderr in suppress_stdout_stderr

#2015 opened 2025-05-07 08:12 by AuroraWright

Added support for overriding tensor buffer types

#2007 opened 2025-04-29 14:15 by zpin

feat: Add Gemma3 chat handler (#1976)

#1989 opened 2025-03-30 19:54 by kossum

fix(types): remove redundant type (typo with repeating lines)

#1971 opened 2025-03-15 16:09 by CHB-0r1s

fix(docker): correct run.sh path in simple Dockerfile

#1911 opened 2025-01-27 13:28 by crufter

feat: add streaming tool use

#1884 opened 2024-12-25 23:17 by lsorber

Add support for XTC and DRY samplers

#1843 opened 2024-11-25 17:19 by zpin

Add musa_simple Dockerfile for supporting Moore Threads GPU

#1842 opened 2024-11-25 11:17 by yeahdongcn

Feat: Support Ranking Method

#1820 opened 2024-11-03 04:50 by yutyan0119

Support LoRA hotswapping and multiple LoRAs at a time

#1817 opened 2024-10-30 10:34 by richdougherty

fix: additional_files support glob patterns

#1800 opened 2024-10-16 05:50 by xianml

Add Paligemma support

#1777 opened 2024-10-02 08:50 by abetlen

fix: handle multiple calls to the same tool

#1758 opened 2024-09-24 15:25 by jeffmaury

Remove unnecessary pyproject optional dependency

#1718 opened 2024-08-30 17:13 by LecrisUT

feat: adding support for external chat format contribution

#1716 opened 2024-08-29 20:12 by axel7083

Allow server to accept openai's new structured output "json_schema" format.

#1677 opened 2024-08-13 07:53 by cerealbox

Add stream_options support according to OpenAI API

#1552 opened 2024-06-25 06:42 by tpfau

Workflow update - PART 2

#1515 opened 2024-06-06 22:21 by Smartappli

Integrate Functionary v2.5 + Refactor Functionary Code

#1509 opened 2024-06-05 15:36 by jeffrey-fong

Support parallel function calls with tool_choice

#1503 opened 2024-06-02 20:55 by CISC

Support multiple chat templates - step 2

#1440 opened 2024-05-09 23:08 by CISC

LLaMA cpp python server: IPV6 support

#1427 opened 2024-05-03 20:18 by Smartappli

fix: add binding for name in ChatCompletionRequestToolMessage

#1407 opened 2024-04-29 20:34 by JDScript

Improve function calling (auto selection, parallel functions)

#1351 opened 2024-04-17 13:35 by themrzmaster

Add user-assistant chat format

#1281 opened 2024-03-17 21:16 by DrewWalkup

Exposes json_schema_to_gbnf method for importing from module

#1212 opened 2024-02-23 12:23 by lukestanley