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 supported62 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bugfix][LoRA][MoE] Use int64 token offsets in MoE-LoRA Triton kernels
- [Bug]: V2 runner handles KV preemptions after request updates can overwrite pages
- [Bug]: Qwen3.6-35B-A3B-FP8 model with TP 4 gives gibberish output !!!!!!!!!!!! on Intel B70 cards
- [Perf][DSv4.1] Small-head sparse decode on SM90
- [ROCm][Perf] Allow DSA indexer native decode above next_n=2
- [Bugfix] Reject `max_tokens < 1` in `BeamSearchParams`
- [Docs] Document attention backends built by the composite factory
- [ROCm][Perf] AITER FlyDSL kernels for the QSA indexer and sparse GQA
- [ROCm][Perf][Qwen4Exp] Dispatch HC combine_and_mix to the AITER FlyDSL two-stage kernel
- [Feature][Frontend] Add periodic usage updates to Anthropic streaming
- Docs
- Python not yet supported