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 supported26 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Bugfix] Respect ignore_eos for GPT-OSS Harmony stop tokens
- [MRV2] enable lora for cuda graph
- [ROCm][CI] Skip ROCm batch invalid-input test pending torch fix
- [Test] Add MTP acceptance-length regression test for DeepSeek-V3 (4xB200 FP8)
- [XPU] enable fp8 with torch._scaled_mm
- [Perf] Use numpy zero-copy path for embedding float response serialization
- [MM][CG] Support encoder CUDA graphs for Step3-VL
- [Bugfix] DelegatingParser: strip buffered end-token text in phase B (follow-up to #41068)
- [BugFix] Wrap TokenizersBackend fallback with cached tokenizer
- File system secondary tier implemented in python
- Docs
- Python not yet supported