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 supported36 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Installation]: Worker processes hang in CPU deadloop after NCCL initialization when loading DeepSeek-V4-Flash-0731 with vLLM V1 engine on H100
- Fix missing q_scale fallback for FP8 KV cache
- [Frontend] Support allowed_tools in Rust chat requests
- [Bugfix] Make DSV4 sparse MLA work end-to-end for plain decode, MTP, and DSpark
- [Perf] Avoid a per-prefill-step GPU->CPU sync in the KDA chunk kernels
- [CPU][MoE] Support DeepSeekV3 routing and group-size-32 INT4 checkpoints
- [Feature] Add PP-first placement for multiprocess serving
- [Bug]: RustToolParser streaming can drop buffered text at stream end
- [Model] Add K-EXAONE-2.0-750B-A37B-DSpark
- [Test] Extend shared tool-parser parity suite to 6 more parsers
- Docs
- Python not yet supported