Ecosyste.ms: Issues

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

GitHub / gpustack/gpustack issues and pull requests

#870 - fix: lock install openfst version

Pull Request - State: closed - Opened by aiwantaozi 22 days ago

#869 - Support Hygon DCU

Issue - State: open - Opened by pengjiang80 22 days ago
Labels: enhancement

#869 - Support Hygon DCU

Issue - State: open - Opened by pengjiang80 22 days ago
Labels: enhancement

#868 - The GPU temperature of Mac Mini M4 cannot be obtained

Issue - State: open - Opened by linyinli 22 days ago - 1 comment
Labels: bug

#868 - The GPU temperature of Mac Mini M4 cannot be obtained

Issue - State: open - Opened by linyinli 22 days ago - 1 comment
Labels: bug

#867 - pip failed to build package: pynini with openfst 1.8.4 on the macOS

Issue - State: closed - Opened by linyinli 23 days ago - 1 comment
Labels: install script

#866 - fix: add tensor parallel size check

Pull Request - State: closed - Opened by aiwantaozi 23 days ago

#866 - fix: add tensor parallel size check

Pull Request - State: closed - Opened by aiwantaozi 23 days ago

#865 - Whisper Model Import Issue

Issue - State: open - Opened by akashengine 23 days ago - 1 comment
Labels: bug

#865 - Whisper Model Import Issue

Issue - State: open - Opened by akashengine 23 days ago - 1 comment
Labels: bug

#864 - Do not follow tail of logs when viewing previous logs

Issue - State: open - Opened by gitlawr 23 days ago - 4 comments
Labels: bug, ui

#862 - chore: bump parser

Pull Request - State: closed - Opened by gitlawr 23 days ago

#862 - chore: bump parser

Pull Request - State: closed - Opened by gitlawr 23 days ago

#861 - WARNING - RPC server for GPU 0 is not running, pid 20568, restarting

Issue - State: open - Opened by addisjeams 24 days ago - 8 comments
Labels: question

#857 - feat: support querying non-category models

Pull Request - State: closed - Opened by gitlawr 26 days ago

#857 - feat: support querying non-category models

Pull Request - State: closed - Opened by gitlawr 26 days ago

#856 - feat: support querying model metadata

Pull Request - State: closed - Opened by gitlawr 26 days ago

#856 - feat: support querying model metadata

Pull Request - State: closed - Opened by gitlawr 26 days ago

#855 - Set default parameters according to model metadata in playground UI

Issue - State: open - Opened by gitlawr 26 days ago
Labels: enhancement

#854 - The model dropdown list in the chat playground is incorrect

Issue - State: closed - Opened by Finenyaco 26 days ago - 3 comments
Labels: bug-qa

#853 - Sometimes the model instance logs are not displayed completely

Issue - State: open - Opened by Finenyaco 26 days ago
Labels: bug, ui

#853 - Sometimes the model instance logs are not displayed completely

Issue - State: closed - Opened by Finenyaco 26 days ago - 1 comment
Labels: bug, ui

#852 - When the request exceeds the available context size, no error message is displayed

Issue - State: closed - Opened by Finenyaco 26 days ago - 2 comments
Labels: bug

#852 - When the request exceeds the available context size, no error message is displayed

Issue - State: closed - Opened by Finenyaco 26 days ago - 2 comments
Labels: bug

#851 - fix: skip gpu count calculation while user defined

Pull Request - State: closed - Opened by aiwantaozi 26 days ago

#851 - fix: skip gpu count calculation while user defined

Pull Request - State: closed - Opened by aiwantaozi 26 days ago

#850 - chore: bump vllm

Pull Request - State: closed - Opened by gitlawr 26 days ago

#850 - chore: bump vllm

Pull Request - State: closed - Opened by gitlawr 26 days ago

#849 - Optimize scheduling failure information and resource utilization

Issue - State: open - Opened by pengjiang80 26 days ago
Labels: enhancement

#848 - Loop in pipx installation in Tencent Cloud Ubuntu 22.04 VM

Issue - State: open - Opened by pengjiang80 27 days ago - 2 comments
Labels: bug

#848 - Loop in pipx installation in Tencent Cloud Ubuntu 22.04 VM

Issue - State: closed - Opened by pengjiang80 27 days ago - 5 comments
Labels: bug

#847 - feat: support select multiple gpus

Pull Request - State: closed - Opened by aiwantaozi 27 days ago

#845 - feat: customizable model categories

Pull Request - State: closed - Opened by gitlawr 27 days ago - 1 comment

#845 - feat: customizable model categories

Pull Request - State: closed - Opened by gitlawr 27 days ago - 1 comment

#844 - AMD GPU utilization reaches 100% when using llama-box as the backend

Issue - State: open - Opened by Finenyaco 27 days ago - 9 comments
Labels: enhancement

#843 - docs: update supported amd devices

Pull Request - State: closed - Opened by aiwantaozi 27 days ago

#842 - fix: handle alias paths in middlewares

Pull Request - State: closed - Opened by gitlawr 27 days ago

#842 - fix: handle alias paths in middlewares

Pull Request - State: closed - Opened by gitlawr 27 days ago

#841 - Model replies with garbled characters when using CPU offloading

Issue - State: closed - Opened by venton-luo 27 days ago - 13 comments
Labels: bug

#840 - chore: switch multi-worker and partial cpu priority

Pull Request - State: closed - Opened by gitlawr 27 days ago

#840 - chore: switch multi-worker and partial cpu priority

Pull Request - State: closed - Opened by gitlawr 27 days ago

#839 - chore: pin builtin backend version

Pull Request - State: closed - Opened by gitlawr 27 days ago

#839 - chore: pin builtin backend version

Pull Request - State: closed - Opened by gitlawr 27 days ago

#838 - fix: update vllm model estimation

Pull Request - State: closed - Opened by gitlawr 28 days ago

#834 - Windows 11 can't run model with vllm

Issue - State: closed - Opened by hlj 28 days ago - 2 comments
Labels: question

#833 - chore: update known embedding models

Pull Request - State: closed - Opened by gitlawr 29 days ago

#833 - chore: update known embedding models

Pull Request - State: closed - Opened by gitlawr 29 days ago

#832 - feat: add model catalog

Pull Request - State: closed - Opened by gitlawr 29 days ago

#831 - fix: scheduler failed to estimate audio model with local path

Pull Request - State: closed - Opened by aiwantaozi 29 days ago

#831 - fix: scheduler failed to estimate audio model with local path

Pull Request - State: closed - Opened by aiwantaozi 29 days ago

#828 - Change the API path in view code sample from /v1-openai to /v1

Issue - State: open - Opened by pengjiang80 30 days ago
Labels: enhancement

#828 - Change the API path in view code sample from /v1-openai to /v1

Issue - State: open - Opened by pengjiang80 30 days ago
Labels: enhancement

#827 - ci: add workflow_dispatch

Pull Request - State: closed - Opened by gitlawr 30 days ago

#827 - ci: add workflow_dispatch

Pull Request - State: closed - Opened by gitlawr 30 days ago

#826 - feat: support vlm in box

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

#826 - feat: support vlm in box

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

#825 - docs: update index

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

#824 - chore: bump box

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

#823 - docs: add suggested parameters for supported diffusion models

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

#822 - HELP！！Whether Linux can be installed in the Conda virtual environment？

Issue - State: open - Opened by eightfeetfish about 1 month ago - 23 comments
Labels: question

#821 - Gpustack cannot work with fastgpt

Issue - State: closed - Opened by linuxliker about 1 month ago - 6 comments
Labels: bug

#820 - feat: tool calling for llama-box

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

#819 - Support vision language models in llama-box backend

Issue - State: closed - Opened by gitlawr about 1 month ago - 1 comment
Labels: enhancement

#818 - 华为显卡910B部署Qwen72B，显存占用只增不减的问题。

Issue - State: open - Opened by azooly about 1 month ago - 4 comments
Labels: bug

#817 - docs: update port range

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

#816 - Support CUDA 11

Issue - State: open - Opened by gitlawr about 1 month ago
Labels: enhancement

#813 - fix: set path in python preparation

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

#812 - chore: add issue translator

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

#811 - --ctx-size is not usefull on embedding for llama-box engine

Issue - State: closed - Opened by verigle about 1 month ago - 3 comments
Labels: bug

#810 - Embedding model classification is messy

Issue - State: closed - Opened by shatang123 about 1 month ago - 3 comments
Labels: bug

#809 - docs: update installation requirements

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

#807 - docs: add modelscope diffusion model collection

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

#806 - Bypass initialisation/download check?

Issue - State: closed - Opened by Lex-au about 1 month ago - 4 comments
Labels: question

#805 - docs: update python version

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

#805 - docs: update python version

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

#804 - Error migrating v0.4.0 to v0.4.1

Issue - State: open - Opened by James4Ever0 about 1 month ago - 6 comments
Labels: bug

#803 - fix: recheck python after installing pipx

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

#803 - fix: recheck python after installing pipx

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

#802 - support vllm to select GPU more than ones

Issue - State: open - Opened by verigle about 1 month ago - 1 comment
Labels: enhancement