Skip to content

Issues: vllm-project/vllm-ascend

[main] vllm-ascend Roadmap Q1 2025
#71 opened Feb 17, 2025 by Yikun
Open 2
[v0.7.1rc1] FAQ & Feedback
#19 opened Feb 8, 2025 by Yikun
Open 10
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

26 Open 19 Closed
26 Open 19 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

[RFC]: Add support for custom ops feature request
#156 opened Feb 25, 2025 by Yikun
@wangxiyuan
[Installation]: 910B3 import toch_npu 出现段错误 installation
#154 opened Feb 25, 2025 by mhqmhy
3
[Bug]: ImportError: libatb.so: cannot open shared object file: No such file or directory question Further information is requested
#152 opened Feb 24, 2025 by phellonchen
6
[Doc]: Can not useTP PP in tihs Version bug Something isn't working question Further information is requested
#148 opened Feb 24, 2025 by shuowoshishui
3
[Bug]: MRotaryEmbedding.get_input_positions() got an unexpected keyword argument 'image_token_id' bug Something isn't working
#145 opened Feb 23, 2025 by SHYuanBest
3
[Installation]: 910B部署vllm-ascend启动失败 installation
#143 opened Feb 22, 2025 by ahutkai
4
[Misc]: Bump CANN version to CANN 8.1.RC1.alpha001 ci/build
#142 opened Feb 22, 2025 by Yikun
RuntimeError: Prefix cache and chunked prefill are currently not supported feature request
#133 opened Feb 21, 2025 by dawnranger
3
Qwen2.5-VL-7B的问题 bug Something isn't working
#131 opened Feb 21, 2025 by ffanyt
2
Failed to infer device type question Further information is requested
#130 opened Feb 21, 2025 by Qukka0914
17
期望开发lora支持的时候，同步支持openai接口的multi-lora！ feature request
#126 opened Feb 21, 2025 by caijijuhe
DeepSeek-R1 on 0.7.1-dev with Torch not compiled with CUDA enabled question Further information is requested
#122 opened Feb 20, 2025 by ColdeZhang
8
Quantization error while running Deepseek-V3-w8a8 feature request
#119 opened Feb 20, 2025 by ApsarasX
6
[Bug]: Qwen2-VL-72B-Instruct Inference failure bug Something isn't working
#115 opened Feb 19, 2025 by invokerbyxv
3
Inference speed is slow performance
#111 opened Feb 19, 2025 by junming-yang
6
how to do multi node deployment installation
#106 opened Feb 19, 2025 by gameofdimension
5
Add a turtorial for Qwen 2.5-VL documentation Improvements or additions to documentation help wanted Extra attention is needed
#75 opened Feb 17, 2025 by Yikun
[New Model]: DeepSeek V3 / R1 new model
#72 opened Feb 17, 2025 by Yikun
@wangxiyuan
2
[main] vllm-ascend Roadmap Q1 2025
#71 opened Feb 17, 2025 by Yikun
24 of 34 tasks
2
Speculative decoding not working feature request
#47 opened Feb 11, 2025 by michelemarzollo
2
Abnormal First Token Output on 910B GPU during Inference bug Something isn't working
#46 opened Feb 11, 2025 by Jozenn
6
Atlas 800 推理服务器（型号：3000）安装失败 feature request
#37 opened Feb 11, 2025 by niejingwei
1
Question about the difference of inference results between NPU and GPU bug Something isn't working
#31 opened Feb 11, 2025 by AIR-hl
6
Add doc for benchmark and profiling on Ascend NPU documentation Improvements or additions to documentation
#26 opened Feb 10, 2025 by Yikun
1
[v0.7.1rc1] FAQ & Feedback
#19 opened Feb 8, 2025 by Yikun
10
ProTip! Type g p on any issue or pull request to go back to the pull request listing page.