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
- [Perf][Multimodal] Use FA4 for long-sequence ViT attention on Hopper
- [Bugfix] Re-probe the tier for new requests instead of reusing a cached miss in tiering AsyncLookupManager
- [XPU][Quantization] Support asymmetric (sym=false) GPTQ int4 linear layers on XPU
- [Bugfix] Reject prompts that cannot be scheduled without chunked prefill
- [Bugfix] Apply the missing prefill decay step in lightning attention
- [Bugfix][Model] Preserve MiDashengLM's untied decoder default
- [Core][Scheduler] Context-aware long prefill chunking
- [Feature][DSv4.1][NIXL] Enable PCP Prefill with NIXL P/D
- [Simulator] Add vLLM Simulator for hardware-aware serving simulation on CPU
- [Metrics] Preserve fractional counter values in snapshots
- Docs
- Python not yet supported