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 supported49 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Refactor][Core] Use torch's device-agnostic streams and events in the V2 model runner
- Add MoE tuning config for RTX PRO 6000 Blackwell (E=512,N=512,fp8_w8a8)
- [ROCm][MoRIIO] Release write-prefill blocks when sidelined
- [Benchmark] Record model_id in bench latency/throughput --output-json
- Enable gated RMSNorm decode fast path for Qwen3.5/3.6-A3B on XPU
- [Bugfix][Model Loader] Support reload_weights with runai_streamer load format
- docs: clarify NIXL KV connector metrics aggregation semantics
- [CI Failure]: (MI355) Core Operation Kernels Shard 1: kernels/test_concat_mla_q.py::test_concat_mla_q_fp8_nope_and_rope
- [Bug]: Cross-encoder `padding="max_length"` produces incorrect `token_type_ids`
- [Bug]: `--api-key` is bypassed by `/invocations`, unauthenticated inference on a server that requires a key
- Docs
- Python not yet supported