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 supported48 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- Segmented prefill for gapped external KV cache hits
- [Core][Feat] Add max-waiting-queue-length parameter to reject requests when waiting queue is full
- [Bugfix] Add SM 12.1 (Blackwell GB10) support for V1 engine
- PR Title: [Feature] EWSJF: Adaptive Scheduler for Mixed-Workloads (30-50% Throughput Gain)
- [Frontend] Add FP8 output quantization support to FlashAttention backend
- [Feat] Add RMSNorm NvFp4 Quant Operator (#32612)
- [Backend][WIP] Integrate MPK (Mirage) compiler as an experimental execution backend to vLLM
- [ROCm] Group quant RMS norm fusion patterns
- [Feature]: Someone please upstream this gfx1201/RDNA4 FP8 Patch into vllm-rocm
- [RFC]: Path to vLLM 1.0 Release
- Docs
- Python not yet supported