Ecosyste.ms: 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

#1939 - No GPU usage, occupied VRAM but only CPU is working

Issue - State: open - Opened by 0xb1te 3 days ago - 2 comments

#1935 - Using OpenBlas to accelerate has no effect？

Issue - State: open - Opened by buptmengjj 4 days ago

#1933 - I cannot install this package with cuda12.4

Issue - State: open - Opened by BoogonClothman 8 days ago - 3 comments

#1932 - Failed building wheel for llama-cpp-python

Issue - State: open - Opened by pklochowicz 9 days ago - 3 comments

#1931 - `llama.cpp` transfer

Issue - State: open - Opened by d-kleine 10 days ago

#1929 - 0.3.6 (No errors). 0.3.7 Seg Fault?

Issue - State: closed - Opened by icsy7867 11 days ago - 2 comments

#1925 - Please release a cuda build for v0.3.5

Issue - State: open - Opened by ParisNeo 14 days ago - 7 comments

#1921 - Distributed Inference

Issue - State: open - Opened by lipere123 16 days ago - 1 comment

#1916 - How to run CLIP model on GPU?

Issue - State: open - Opened by zhu-j-faceonlive 18 days ago - 1 comment

#1915 - Cuda Build Failed, Please take a look at this

Issue - State: open - Opened by RealUnrealGameDev 20 days ago - 1 comment

#1913 - System.AccessViolationException on llama_backend_init()

Issue - State: closed - Opened by plqplq 24 days ago - 3 comments

#1912 - Migrate to the latest version of llama.cpp APIs and support for DeepSeek models

Pull Request - State: closed - Opened by jaepil 24 days ago - 1 comment

#1911 - fix(docker): correct run.sh path in simple Dockerfile

Pull Request - State: open - Opened by crufter 25 days ago

#1910 - Automate upstream llama.cpp sync

Issue - State: open - Opened by bgs4free 26 days ago - 4 comments

#1909 - Get bug after upgrade v0.3.4 to v0.3.6

Issue - State: closed - Opened by Kar-Su 27 days ago - 1 comment

#1906 - openai API `n` argument is ignored

Issue - State: open - Opened by BenjaminMarechalEVITECH 28 days ago

#1905 - Wrong chat format for llava 1.5

Issue - State: open - Opened by BenjaminMarechalEVITECH 28 days ago

#1904 - Add minicpm-o and qwen2-vl to the list of supported multimodal models.

Issue - State: open - Opened by kseyhan 28 days ago - 9 comments

#1902 - Question - Batch Processing

Issue - State: open - Opened by virentakia about 1 month ago

#1901 - Update llama_cpp: Sync LLAMA_API names with llama.cpp mainline. Needs more testing

Pull Request - State: closed - Opened by JamePeng about 1 month ago - 10 comments

#1900 - DeepSeek-R1-Distill-Qwen-32B-GGUF needs the deepseek-r1-qwen tokenizer

Issue - State: closed - Opened by Kenshiro-28 about 1 month ago - 13 comments

#1899 - chore(deps): bump conda-incubator/setup-miniconda from 3.1.0 to 3.1.1

Pull Request - State: open - Opened by dependabot[bot] about 1 month ago
Labels: dependencies, github_actions

#1898 - Fix error showing time spent in llama perf context print

Pull Request - State: closed - Opened by shakalaca about 1 month ago

#1897 - Generate answer from embedding vectors

Issue - State: open - Opened by leewoosub about 1 month ago

#1895 - Does it support the gguf format model of Qwen2-VL-2B-Instruct

Issue - State: open - Opened by helloHKTK about 1 month ago - 5 comments

#1894 - Fix the CUDA workflow

Pull Request - State: closed - Opened by oobabooga about 1 month ago

#1893 - cohere2 architecture issue

Issue - State: open - Opened by MertcanTekin about 1 month ago

#1892 - Dependency issues with uvicorn

Issue - State: open - Opened by jaslatendresse about 1 month ago - 4 comments

#1889 - Implementation doubt

Issue - State: open - Opened by lmbelo about 2 months ago - 1 comment

#1888 - The C compiler identification is unknown

Issue - State: open - Opened by makrse about 2 months ago

#1886 - MiniCPM-V 2.6 memory leak occurred !!!

Issue - State: open - Opened by Liwx1014 about 2 months ago - 3 comments

#1884 - feat: add streaming tool use

Pull Request - State: open - Opened by lsorber about 2 months ago - 5 comments

#1883 - Feature request: add support for streaming tool use

Issue - State: open - Opened by lsorber about 2 months ago

#1882 - CUDA not detected when running without --gpus all

Issue - State: closed - Opened by nandhiniramanan5 about 2 months ago - 3 comments

#1881 - How to create .so file for llama-cpp-python please help!

Issue - State: open - Opened by ayush20501 about 2 months ago

#1880 - ROCM Build Target or Build Instructions are incorrect

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

#1879 - Fix/correct streaming resource lock

Pull Request - State: closed - Opened by gjpower 2 months ago - 3 comments

#1878 - new

Pull Request - State: open - Opened by Harshitha110809 2 months ago

#1877 - Update Dockerfile

Pull Request - State: open - Opened by Smartappli 2 months ago

#1876 - issue tying to install on WSL

Issue - State: open - Opened by silvacarl2 2 months ago - 4 comments

#1874 - Setting verbose=False issues with threads

Issue - State: open - Opened by jeberger 2 months ago - 1 comment

#1871 - fix: replace anyio.Lock with asyncio.Lock to resolve lock handling issues

Pull Request - State: closed - Opened by sergey21000 2 months ago - 3 comments

#1870 - Mambaforge breaks cuda builds, switch to miniforge?

Issue - State: open - Opened by fat-tire 2 months ago - 1 comment

#1868 - Default temperature for llama-cpp-python server

Issue - State: closed - Opened by Qsan1 2 months ago - 2 comments

#1867 - Updated ROCm installation instructions

Pull Request - State: open - Opened by agronholm 2 months ago

#1864 - Add: Include option to normalize & truncate embeddings in create_embe…

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

#1862 - Fix: Refactor AsyncExitStack usage to resolve lock handling errors

Pull Request - State: closed - Opened by sergey21000 2 months ago - 4 comments

#1860 - Add an option to enable --runtime-repack in llama.cpp

Issue - State: closed - Opened by ekcrisp 2 months ago - 4 comments

#1858 - fix: add missing await statements for async exit_stack handling

Pull Request - State: closed - Opened by gjpower 2 months ago

#1854 - Request to publish CUDA builds for v0.3.2 to GitHub Releases

Issue - State: open - Opened by lsorber 3 months ago - 3 comments

#1851 - Intel GPU not enabled when using -DLLAVA_BUILD=OFF

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

#1845 - Fix: add missing 'seed' attribute to llama_context_params initialization

Pull Request - State: closed - Opened by sergey21000 3 months ago - 1 comment

#1844 - chore(deps): bump pypa/cibuildwheel from 2.21.1 to 2.22.0

Pull Request - State: closed - Opened by dependabot[bot] 3 months ago
Labels: dependencies, github_actions

#1843 - Add support for XTC and DRY samplers

Pull Request - State: open - Opened by zpin 3 months ago - 3 comments

#1842 - Add musa_simple Dockerfile for supporting Moore Threads GPU

Pull Request - State: open - Opened by yeahdongcn 3 months ago

#1838 - Fix: CUDA workflow actions

Pull Request - State: closed - Opened by pabl-o-ce 3 months ago - 1 comment

#1837 - Error when update to 0.3.2

Issue - State: closed - Opened by paoloski97 3 months ago

#1836 - Release the GIL

Issue - State: closed - Opened by simonw 3 months ago - 3 comments

#1835 - updated from 0.2.90 to 0.3.2 and now my GPU won't load

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

#1834 - use n_threads param to call _embed_image_bytes fun

Pull Request - State: open - Opened by KenForever1 3 months ago

#1833 - Update dev instrunction

Pull Request - State: closed - Opened by Florents-Tselai 3 months ago

#1832 - Mistral-instruct not using system prompt.

Issue - State: closed - Opened by AkiraRy 3 months ago - 2 comments

#1830 - "eval time" and "prompt eval time" is 0.00ms after Ver0.3.0

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

#1827 - Update related llama.cpp to support Intel AMX instruction

Issue - State: closed - Opened by nai-kon 3 months ago - 1 comment

#1826 - llama-server not using GPU

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

#1825 - Update README.md

Pull Request - State: open - Opened by Nik-Kras 4 months ago - 3 comments

#1824 - Request for prebuilt CUDA wheels for newer version

Issue - State: closed - Opened by XJF2332 4 months ago - 10 comments

#1822 - Prebuilt CUDA wheels not working

Issue - State: open - Opened by mjwweb 4 months ago - 2 comments

#1821 - chore(deps): bump conda-incubator/setup-miniconda from 3.0.4 to 3.1.0

Pull Request - State: closed - Opened by dependabot[bot] 4 months ago
Labels: dependencies, github_actions