Data

Tools

Indexes

Applications

Experiments

Issues

An open API service for providing issue and pull request metadata for open source projects.

GitHub / abetlen/llama-cpp-python issues and pull requests

#2133 - feat: Qwen 3.5 GDN support with hybrid model fixes

Pull Request - State: open - Opened by r-dh 6 days ago - 1 comment

#2132 - feat: update llama.cpp submodule and bindings for Qwen 3.5 support

Pull Request - State: open - Opened by codavidgarcia 6 days ago - 1 comment

#2131 - feat: Add DeepSeek R1 and distilled model support

Pull Request - State: open - Opened by ljluestc 9 days ago

#2123 - Up to date llama.cpp wheel here (native libraries)

Issue - State: open - Opened by mdjou 25 days ago

#2114 - Add new maintainers and/or archive this project

Issue - State: open - Opened by davidmezzetti about 2 months ago - 8 comments

#2108 - Update to llama.cpp 2026-01-01

Pull Request - State: open - Opened by avion23 2 months ago - 27 comments

#2107 - Build error with LLGUIDANCE

Issue - State: open - Opened by JeremyBickel 3 months ago

#2105 - Support for LFM2-VL models

Issue - State: open - Opened by Borzyszkowski 3 months ago - 1 comment

#2104 - LLM Loading Failure — AttributeError in LlamaModel.__del__

Issue - State: open - Opened by 2P2O5 3 months ago - 2 comments

#2103 - Pre-built wheels for Python 3.14 and 3.14 free-threaded

Issue - State: open - Opened by clemlesne 3 months ago - 1 comment

#2098 - Add support for Qwen3-vl models

Issue - State: open - Opened by Hansashawn 3 months ago - 4 comments

#2096 - There is a bug in urlopen() when using image_url with credentials.

Issue - State: open - Opened by WHJ125 3 months ago - 1 comment

#2093 - Can't not enable KLEIDIAI Feature after 0.3.10

Issue - State: closed - Opened by ZIFENG278 4 months ago

#2091 - cu128 wheel

Issue - State: open - Opened by CyberSys 4 months ago - 1 comment

#2090 - vulkan - windows

Issue - State: open - Opened by jwijffels 4 months ago - 3 comments

#2087 - 'LlamaModel' object has no attribute 'sampler'

Issue - State: closed - Opened by raheel-shahzad 4 months ago - 1 comment

#2085 - Fixed issue #1938

Pull Request - State: open - Opened by TNing 4 months ago

#2083 - Include x64 directory for CUDA DLLs on Windows

Pull Request - State: open - Opened by ajparsons 5 months ago

#2082 - Implement GenerationTagIgnore Jinja2 extension

Pull Request - State: open - Opened by hidehiroanto 5 months ago

#2081 - how to compile on last gcc?

Issue - State: open - Opened by wipedlifepotato 5 months ago - 1 comment

#2080 - Feature Request: support qwen3-vl series

Issue - State: open - Opened by dahwin 5 months ago - 23 comments

#2078 - Direct image input via PIL instead of Base64

Issue - State: open - Opened by rudolphos 5 months ago

#2077 - support batch embeddings and zero-copy numpy returns

Pull Request - State: closed - Opened by kavorite 5 months ago - 1 comment

#2076 - Periodic alignment with upstream

Issue - State: open - Opened by handshape 5 months ago

#2075 - Support for MiniCPM-V 4.5

Issue - State: open - Opened by eximius313 5 months ago

#2072 - Fixed a few typos in README.md

Pull Request - State: open - Opened by ImadSaddik 5 months ago

#2071 - Llama.cpp@tags/b6490

Pull Request - State: open - Opened by LongStoryMedia 6 months ago

#2066 - Better Qwen2.5-VL chat template.

Pull Request - State: open - Opened by alcoftTAO 6 months ago

#2065 - unknown model architecture: 'gemma-embedding'

Issue - State: open - Opened by mariocannistra 6 months ago - 4 comments

#2064 - llama_get_kv_self debug symbols removed

Issue - State: open - Opened by Bread7 6 months ago

#2063 - Thinking toggle support for Qwen related models

Issue - State: open - Opened by Kishlay-notabot 6 months ago - 1 comment

#2061 - ERROR installing v0.3.16 with CUDA enabled on docker

Issue - State: open - Opened by arditobryan 6 months ago - 2 comments

#2059 - fix chat handler class name in docs

Pull Request - State: open - Opened by anakin87 7 months ago

#2058 - Fix multi-sequence embeddings

Pull Request - State: open - Opened by iamlemec 7 months ago - 2 comments

#2056 - Update hyperlink to llama.cpp build docs

Pull Request - State: open - Opened by SleepyYui 7 months ago

#2054 - cannot run fine-tuned gpt-oss model correctly

Issue - State: open - Opened by jiachenguoNU 7 months ago

#2053 - cannot run fine-tuned gpt-oss model correctly

Issue - State: closed - Opened by jiachenguoNU 7 months ago

#2052 - Adding Audio capabilities

Issue - State: open - Opened by haixuanTao 7 months ago

#2051 - Can't compute multiple embeddings in a single call

Issue - State: open - Opened by jeberger 7 months ago - 4 comments

#2049 - Small updates to allow for `gpt-oss` generation

Pull Request - State: open - Opened by iamlemec 7 months ago

#2046 - fix: rename op_offloat to op_offload in llama.py

Pull Request - State: closed - Opened by sergey21000 7 months ago

#2044 - Add timeout and error handling in FastAPI uvicorn server

Pull Request - State: open - Opened by amandwivedi45 8 months ago

#2041 - Improve error message when model file is missing

Pull Request - State: open - Opened by NITHIN0710 8 months ago

#2040 - Better chat format for Qwen2.5-VL

Pull Request - State: open - Opened by alcoftTAO 8 months ago

#2040 - Better chat format for Qwen2.5-VL

Pull Request - State: open - Opened by alcoftTAO 8 months ago

#2039 - ARM Runners support CUDA SBSA

Pull Request - State: open - Opened by johnnynunez 8 months ago

#2038 - Inferencing Flan-T5 - GGML_ASSERT error

Issue - State: open - Opened by railesDev 8 months ago

#2037 - Error calling `llama_kv_cache_clear` in llama.py with 0.3.10

Issue - State: closed - Opened by davidmezzetti 8 months ago - 2 comments

#2036 - Fail to install llama

Issue - State: closed - Opened by Deeffyy 8 months ago - 3 comments

#2029 - Access Violation issue facing for exe created using pyinstaller

Issue - State: open - Opened by maniron214 9 months ago - 3 comments

#2027 - Update fork

Pull Request - State: closed - Opened by benzlokzik 9 months ago - 1 comment

#2027 - Update fork

Pull Request - State: open - Opened by benzlokzik 9 months ago

#2026 - llama_cpp/lib/libllama.so: undefined symbol: llama_kv_cache_view_init

Issue - State: open - Opened by opsec-ai 9 months ago - 3 comments

#2025 - Fix disk-cache LRU logic

Pull Request - State: open - Opened by donbcd 9 months ago

#2025 - Fix disk-cache LRU logic

Pull Request - State: open - Opened by donbcd 9 months ago

#2024 - Build is broken in fedora 42 arm64

Issue - State: closed - Opened by paul-civitas 9 months ago - 1 comment

#2023 - Support for jinja for custom chat templates

Issue - State: open - Opened by Z1EMN1AK 10 months ago - 1 comment

#2018 - Add support for Cohere Command models

Pull Request - State: open - Opened by handshape 10 months ago - 1 comment

#2018 - Add support for Cohere Command models

Pull Request - State: open - Opened by handshape 10 months ago

#2016 - Macos wheel fails on 0.35, works on 0.34

Issue - State: open - Opened by Alex-EEE 10 months ago

#2015 - Flush libc stdout/stderr in suppress_stdout_stderr

Pull Request - State: open - Opened by AuroraWright 10 months ago

#2015 - Flush libc stdout/stderr in suppress_stdout_stderr

Pull Request - State: open - Opened by AuroraWright 10 months ago

#2014 - Is llama-cpp-python supports Llama-4?

Issue - State: open - Opened by rbgo404 10 months ago

#2013 - Can't install with GPU support with Cuda toolkit 12.9 and Cuda 12.9

Issue - State: open - Opened by hunainahmedj 10 months ago - 19 comments

#2012 - How to install the latest version with GPU support

Issue - State: open - Opened by shigabeev 10 months ago

#2010 - llama-cpp-python 0.3.8 with CUDA

Issue - State: open - Opened by SeBL4RD 10 months ago

#2009 - Créer haba

Pull Request - State: closed - Opened by neuroQuantu 10 months ago - 2 comments

#2008 - Qwen 3 model not working

Issue - State: closed - Opened by Kenshiro-28 10 months ago - 13 comments