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 supported42 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [KVConnector] Add prefix-length threshold for lazy SimpleCPUOffloadConnector
- Whisper : use `<|startofprev|>` instead of `<|prev|>`
- Add tuned fused_moe config for Nemotron-Super on H200
- [RFC]: MTP speculative decoding under pipeline parallelism (PP>1)
- [Bug]: V1 prefix-cache extra-key domain collision between LoRA name and cache_salt
- 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
- 💥 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
- Docs
- Python not yet supported