Pull Requests abetlen/llama-cpp-python

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

Fixed typo at line 340 of README.md

#1791 opened 2024-10-09 20:14 by Victoran0

server types: Move 'model' parameter to clarify it is used

#1786 opened 2024-10-05 23:54 by domdomegg

Fix LLAVA_CPP_LIB creating empty path

#1782 opened 2024-10-03 09:18 by navratil-matej

Add Paligemma support

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

Update Dockerfile

#1776 opened 2024-10-01 11:30 by Smartappli

fix: handle multiple calls to the same tool

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

corrected command

#1739 opened 2024-09-12 08:58 by Shehrozkashif

Resync llama_grammar with llama.cpp implementation and use curly braces quantities instead of repetitions

#1721 opened 2024-08-31 20:39 by gbloisi-openaire

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 Ruff Linter

#1651 opened 2024-08-02 15:16 by Smartappli

Support images from local storage for Llava models

#1583 opened 2024-07-09 09:28 by GokulMuraliRajasekar

Add stream_options support according to OpenAI API

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

Change server approach to handle parallel requests

#1550 opened 2024-06-24 08:00 by sergey-zinchenko

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

Chat template rendering extensions to match transformers

#1486 opened 2024-05-26 06:56 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

Add the Command R chat format

#1382 opened 2024-04-25 10:22 by euxoa

Improve function calling (auto selection, parallel functions)

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

Feature: Lightweight llama_cpp.server Docker Image Build Workflow

#1331 opened 2024-04-05 16:56 by devcxl

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

WIP: Parallel generation implemenation

#1209 opened 2024-02-22 05:15 by iamlemec