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 supported62 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: Hunyuan A13B streaming leaks `</answer>` into `content`
- [Bugfix][XPU] Forward num_splits to the XPU flash attention kernel
- [Bugfix][ROCm] Force Triton MXFP4 for 96-row ASM scale tiles
- [Perf][Attention] DiffKV: group spec-verify only when the split-KV grid is large
- [Observability] Use $__rate_interval for rate() in Grafana performanc…
- [Bug]: vLLM does not ignore temperature, presence_penalty, and frequency_penalty for DeepSeek V4 series thinking mode, unlike the official DeepSeek API
- [Bugfix][Quantization] Warn when DeepGEMM requantizes fp32 block scales to UE8M0
- [Docs] Feedback for `/en/stable/serving/data_parallel_deployment/` load balancing with respect to vllm-router
- [Feature]: Add a built-in JSON logging formatter
- [Doc] Clarify keep-mode pause and clear_cache semantics
- Docs
- Python not yet supported