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 supported37 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Performance]: FlashInfer NVFP4 KV cache causal prefill is ~1.7-1.8x slower than FP8 on SM120
- [Bugfix][Model Runner V2] Restore multimodal draft capability detection
- [Rust Frontend] Propagate W3C trace headers to engine-core requests
- [Bugfix][Platform] Stop re-initializing NVML on every device-capability check (fixes #50381)
- [kv_offload] Session Aware Eviction Policy
- [Bugfix] [V1] Fix CPU KV offloading segfault on hybrid attention models
- [SM120] Add NVFP4 KV cache support for consumer Blackwell (RTX 5090)
- [Rust Frontend] Add standalone Rust renderer
- [CI] Add option to raise an exception when NaNs are detected in logits
- [ROCm] Enable 12-head MLA persistent decode
- Docs
- Python not yet supported