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 supported61 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Perf] Fuse admission-time staged writes into fewer kernel calls
- [Tracking] DeepEP v2 maturation and legacy DeepEP v1 removal
- [Bugfix] Keep ranks in step when the FlashInfer autotune cache fails to load or save
- [Bug]: DeepSeek V4.1 tool parser drops malformed DSML blocks and emits invalid/empty args on truncation
- [Model] MuseSpark: Ampere (sm80) + AutoRound/GPTQ INT4 experts
- [Beam] Enable CuTeDSL NVFP4 MegaMoE
- Nemotron-3.5 tool calls lose trailing/edge newlines under the wrapped qwen3_coder format (_trim_wrapping_newlines) — needs a compact converter like #58019
- [Performance]: NIXL KV transfer silently falls back to UCX TCP emulation (~0.56 GB/s) on same-host GPUs without peer-to-peer access and no RDMA NIC
- [Benchmark][Attention] Support int8_per_token_head KV cache in attention_benchmarks
- [Perf][Attention] 16-byte-align per-token-head KV slots so Triton vectorizes loads
- Docs
- Python not yet supported