Skip to content

Issues: vllm-project/vllm

[Roadmap] vLLM Roadmap Q4 2024
#9006 opened Oct 1, 2024 by simon-mo
Open 15
vLLM's V2 Engine Architecture
#8779 opened Sep 24, 2024 by simon-mo
Open 7
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

Clear current search query, filters, and sorts
286 Open 217 Closed
286 Open 217 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

[Feature]: Llama 3 and Command-R Chat Templates feature request
#9904 opened Nov 1, 2024 by hammer-ai
1 task done
[Feature]: automatically release graphics card memory feature request
#9903 opened Nov 1, 2024 by turkeymz
1 task done
1
[Feature]: Support guided decoding with multistep decoding feature request
#9893 opened Oct 31, 2024 by joerunde
1 task done
[Feature]: Online video support for VLMs feature request
#9842 opened Oct 30, 2024 by litianjian
1 task done
5
[Feature]: host wheel via pypi index? feature request
#9831 opened Oct 30, 2024 by youkaichao
1 task done
1
[Feature]: Public binary release supports torch 2.5.1 feature request
#9830 opened Oct 30, 2024 by luohao123
1 task done
[Feature]: Integrate Writing in the Margins inference pattern ($5,000 Bounty) feature request
#9807 opened Oct 29, 2024 by melisa-writer
1 task done
3
[Feature]: soft limit-mm-per-prompt for MM OAI API feature request
#9805 opened Oct 29, 2024 by SinanAkkoyun
1 task done
3
[Feature]: Is it supported Qwen2.5 tool_choice: auto? feature request
#9789 opened Oct 29, 2024 by deku0818
1 task done
2
[Feature]: Image-Modality Throughput Benchmark feature request
#9778 opened Oct 28, 2024 by lk-chen
1 task done
1
[Feature]: Qwen2.5 model : ValueError: This model does not support the 'embedding' task. Supported tasks: {'generate'} feature request
#9761 opened Oct 28, 2024 by tarikbeijing
1 task done
1
[Feature]: Support a flush_cache API to clean the kvcache after load_weights feature request
#9744 opened Oct 28, 2024 by zhuzilin
1 task done
1
[Feature]: OpenAI supply image path feature request
#9742 opened Oct 27, 2024 by SinanAkkoyun
1 task done
1
[Feature]: Multiple Secret Keys feature request
#9698 opened Oct 25, 2024 by CHesketh76
1 task done
1
[Feature]: support SageAttention feature request
#9654 opened Oct 24, 2024 by LSC527
1 task done
[Feature]: support for Cambricon MLU feature request
#9649 opened Oct 24, 2024 by a120092009
1 task done
2
[Bug]: preifx cache reuse feature request
#9643 opened Oct 24, 2024 by brotherchen
1 task done
2
[Feature]: support x-request-id header feature request
#9593 opened Oct 22, 2024 by cjackal
1 task done
1
[Feature]: Support for 1.58-bit models. feature request
#9566 opened Oct 21, 2024 by RealMrCactus
1 task done
[Feature]: Support for Controlled Decoding feature request
#9541 opened Oct 21, 2024 by simonucl
1 task done
1
[Feature]: EAGLE fp8 quantization feature request
#9534 opened Oct 20, 2024 by fengyang95
1 task done
2
[Feature]: google/gemma-2-2b supports 8K context length but vllm does not support it. feature request
#9517 opened Oct 18, 2024 by yananchen1989
1 task done
1
[Feature]: LoRA support for InternVLChatModel feature request
#9495 opened Oct 18, 2024 by AkshataABhat
1 task done
13
[Feature]: Support for Diff-Transformer to limit noise in attention calculation @ runtime feature request
#9480 opened Oct 18, 2024 by nightflight-dk
1 task done
[Feature]: Alternating local-global attention layers feature request
#9464 opened Oct 17, 2024 by griff4692
1 task done
1
ProTip! Add no:assignee to see everything that’s not assigned.