Pull Requests abetlen/llama-cpp-python

feat: implement required attributes in json_schema_to_gbnf

#1170 opened 2024-02-09 19:17 by BDav24

Remove subsequences of cached tokens to match a longer prefix

#1106 opened 2024-01-19 06:36 by m42a

explicit cast messages to string for RAG purposes

#1080 opened 2024-01-11 21:42 by nivibilla

Multistage CUDA Dockerfile to reduce image size and allow local repository build

#993 opened 2023-12-10 19:27 by peturparkur

QA Document High api examples

#962 opened 2023-12-01 00:33 by zocainViken

Update shared library import & license compliance

#955 opened 2023-11-29 18:56 by D4ve-R

Add batch inference support (WIP)

#951 opened 2023-11-28 10:00 by abetlen

Replace all absolute imports of llama_cpp in llama_cpp

#922 opened 2023-11-16 21:08 by JohanAR

fix: get system message from messages for all prompt formats

#913 opened 2023-11-15 12:26 by julianullrich99

limit_concurrency Uvicorn

#868 opened 2023-11-03 12:20 by RossAlRed

feat(llm-vscode): add `generate` endpoint to support llm-vscode

#843 opened 2023-10-24 13:33 by joennlae

Add cancel() method to interrupt a stream

#733 opened 2023-09-18 10:17 by simonchatts

gguf reader for layer and size estimates

#716 opened 2023-09-14 14:36 by earonesty

pyinstaller hook script

#709 opened 2023-09-13 19:34 by earonesty

Add Helm-Chart for easy Kubernetes deployment

#678 opened 2023-09-07 20:34 by 3deep5me

Create Dockerfile-CN

#624 opened 2023-08-20 11:59 by Aincvy

Add parameter to skip saving to cache when caching is enabled

#594 opened 2023-08-10 08:36 by shaunabanana

Create simple_local_chat.py

#575 opened 2023-08-05 19:31 by Mrgithub93

Implement a flake.nix that uses the upstream llama.cpp flake by reference

#517 opened 2023-07-23 17:38 by charles-dyfis-net

Create server_streaming.py

#414 opened 2023-06-22 07:40 by zinccat

Added Mirostat Mode and related Params to Llama initialization

#329 opened 2023-06-06 05:13 by CoffeeVampir3

Allow relative paths at model initialization enhancement

#198 opened 2023-05-12 15:17 by andreakiro

WIP: Mechanism to retrieve all logprobs on completion enhancement

#176 opened 2023-05-09 13:40 by tristanvdb

Add truncate to high level api enhancement

#172 opened 2023-05-08 14:35 by SagsMug

added huggingface space implementation enhancement

#146 opened 2023-05-03 11:19 by abhishekmamdapure

(WIP) Openapi client gen enhancement

#144 opened 2023-05-03 00:31 by Stonelinks