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
- [Core] Demo implementation of extensible kv cache memory
- [Bug] Crash input dump leaks structured-output schema at ERROR level
- [Bug] NVFP4 flashinfer_b12x MoE produces empty/garbage output under pipeline or tensor parallel on SM120 — regression between dev552 (06-29) and dev601 (06-30)
- [Bugfix][Logging] Redact structured-outputs schema in crash dumps
- Revert "[CPU][Perf]Added tanh AOR for faster gelu activations." (#44639)
- [Feature]: Detect CUDA toolchain/driver PTX version mismatch at startup and raise an actionable error
- [Performance]: Logprob divergence between vLLM and transformers on a fine-tuned Qwen3.5-VL mobile-use model
- [Bug]: vllm==0.23.0 Qwen3.6-27B, system prompt same in multi requests, But prefix cache failure.
- Revert "[Bugfix][Kernel] Correct FlashInfer CUTLASS MoE tuning token bound" (#46838)
- Draft: Xqa specdec
- Docs
- Python not yet supported