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 supported46 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- feat(api): add optional admin control plane API and CLI
- [Bug]: Spec Decode Stats still report drafted tokens if drafting is skipped
- fix: replace fatal assertions with MultiModalCacheMissError in MM cache
- [Bug][Spec Decode] Fix AR metrics when drafting is skipped
- [Performance]: Remove `batch_size` and `max_seq_len` padding when cuDNN is upgraded to 9.19
- [Feature]: Support structured outputs for beam search
- feat(frontend): support --tool-call-parser=auto for automatic parser detection
- [ROCm] Use supports_fp8() for FP8 feature gates instead of arch checks
- [ROCm] Enable FP8 KV-cache and relax constraints for RDNA4 custom paged attention
- [Feature]: parity with cuda - ROCm Kimi K2.5 disagg PD +wideEP recipe
- Docs
- Python not yet supported