vllm
https://github.com/vllm-project/vllm
Python
A high-throughput and memory-efficient inference and serving engine for LLMs
Triage Issues!
When you volunteer to triage issues, you'll receive an email each day with a link to an open issue that needs help in this project. You'll also receive instructions on how to triage issues.
Triage Docs!
Receive a documented method or class from your favorite GitHub repos in your inbox every day. If you're really pro, receive undocumented methods or classes and supercharge your commit history.
Python not yet supported51 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: deepseek_v4 parser: reply without </think> routes the whole answer to reasoning_content (content empty), trailing EOS not stripped
- [Bugfix][Parser] Fix streaming tool-call args truncated by schema coercion
- [Bugfix] Make Gemma 4 suppress-token masking CUDA-graph safe
- [Bugfix] Avoid FlashAttention 3 with batch invariance on Hopper
- [Bugfix] Share FlashInfer B12x MoE workspace across layers
- Dynamic-fork scheduling, Medusa/MTP spec decode, and InternVL resize for HPD-Parsing (based on v0.17.1)
- [RFC]: GDS support for filesystem KV-cache offloading
- [Bug]: Performance regression caused by high-priority L2 Cache Data Persisting from Server Startup
- [XPU][UT]Convert awq-packed MoE qweight to the gptq-equivalent layout on xpu
- Bump astral-sh/setup-uv from 7.6.0 to 9.0.0
- Docs
- Python not yet supported