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 supported49 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Model] Decoder-side SWA bounded replay for DeepSeek-V4.1
- [Bug]: `/score` Unicode truncation can exceed per-input token limits
- [Perf][ROCm] Force Triton MXFP4 for 96-row ASM scale tiles
- [Perf][Attention] Enable bounded multi-token DiffKV split-KV
- [Bugfix][Model] MiMo: keep fused fp8 qkv_proj pairing state across weight-loading calls
- [Bugfix] Preserve padding token types for cross encoders
- [Observability] Use $__rate_interval for rate() in Grafana performanc…
- [ROCm][DSv4.1] Enable DSpark adaptive verification
- [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
- Python not yet supported