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 supported36 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bugfix][Tool Parser] Preserve whitespace in Step3 parameter values
- [EPLB] Support custom initial expert maps
- [Bug]: FlashInfer b12x SM120 MoE workspace allocated inside `profile_run` → OOM on 16 GB Blackwell (NVFP4 Qwen3.6-35B-A3B); regressed between vLLM dev552/FlashInfer 0.6.12 and v0.25.1/FlashInfer 0.6.13
- [Bug]: vllm bench serve - huggingface datasets - "TypeError: string indices must be integers, not 'str'"
- [Feature]: Support for Responses API `/v1/responses/input_tokens`
- [Perf][Frontend] Skip detokenization 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
- Docs
- Python not yet supported