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 supported51 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: vllm bench serve - huggingface datasets - "TypeError: string indices must be integers, not 'str'"
- [Feature]: Support for Responses API `/v1/responses/input_tokens`
- [Test] Cover detokenize=False in offline beam search
- [Bugfix][Frontend] Support namespace tools for harmony/gpt-oss models in Responses API
- [Bugfix] Shared MM text-LoRA mapper fallback for language_model wrappers
- [Bug]: FlashInfer sampler JIT crashes engine startup when nvcc isn't discoverable (default precompiled/wheel install) — no fallback to native sampler
- Zero JIT compilation during runtime
- [Bug]: Qwen3.5 / Qwen3.6 hybrid-GDN LoRA: vLLM `enable_lora` does not change generations vs base, while HF Peft does
- [Benchmark] Add FP8 block-scaled GEMM to fp8_gemm benchmark
- [Bugfix] Fix Aria garbage output at TP>1: shared experts double all-reduce
- Docs
- Python not yet supported