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
- [Bugfix][Quantization] FP8 Dynamic Block Size Auto-Discovery and Quark Prefix Normalization
- [Bugfix][ROCm] DeepSeek-V4/V4.1: Hybrid FP8/MXFP4 Quant Routing Guard, Fused Shared Experts, Engram Scale Translation, and VLM Generator Streaming
- [Bug]: MTP fails to load dense BF16 MTP head on compressed-tensors pack-quantized checkpoints (no module or parameter named 'fc.weight')
- [Bugfix] Bracket IPv6 hosts in the DP supervisor probe URL
- [Bugfix][Model] Build the Qwen3.5 MTP head unquantized when the checkpoint ships it dense
- [Perf][Model Loader] Fast MoE Tri-Modal Ingestion Engine: Cold NVMe Streaming and Layer-Bounded 3D Bulk DMA
- [Bugfix][Frontend]keep anthropic tool-result images in tool messages
- [Perf][Scheduler] Add risk-aware prefix-cache admission
- [Tracking] Gemma4 AITER QK-norm+RoPE+KVCache fusion + RoPE IR-op migration (ROCm)
- [RFC]: KV cache grouping for hybrid models with speculative drafters
- Docs
- Python not yet supported