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 supported29 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- Benchmark request: mixed long-prefill / long-decode / repeated-prefix serving boundary
- [Performance][ModelOpt] B300 auto backend is suboptimal for Qwen-Image mixed NVFP4
- [Bug][FP8] ScaledMMLinearKernel rejects valid non-contiguous batched activations
- [Feature]: Add support for Bailing MTP speculative decoding
- [Bugfix][Core] Close underlying iterator in merge_async_iterators single-iterator fast path
- 💥 RTX 5090 + WSL2: V1 Engine hangs at startup — EngineCore spawns but never connects via ZMQ, ALL models fail (v0.21-0.22), raw spawn+Pytorch works fine
- CUDA device-side assert with nvidia/Qwen3.6-35B-A3B-NVFP4 + MTP on nightly f91fb2f
- [Opt] Optimize rotary embedding cache length
- [Installation]: ROCm install silently falls back to CUDA abi3 wheel on Python < 3.12 (no ROCm abi3 / cp311 / cp313 wheels)
- [Bug]: thinking_token_budget forces reasoning_end tokens into the middle of tool-call arguments — ThinkingBudgetStateHolder doesn't treat <tool_call> as implicit reasoning end (Qwen3.5+)
- Docs
- Python not yet supported