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 supported13 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Feature]: MoE Layer
- [Bug][ModelOpt]: Llama4 DP/EP FlashInfer Cutlass Is Broken
- [RFC]: Decouple page_size_bytes calculation in AttentionSpec for TPU/RPA Compatibility
- [Bug]: enable_chunked_prefill=True causes hang in AsyncLLM which is affected by disable_log_stats=True
- [Usage]: How can I use GPU12 as standalone KV LMCache?
- [Bug]: Engine crash with MTP + CUDA-Graph for Qwen3-Next (concurrent requests = 3)
- [RFC]: Integrate omni-ai-npu/omni-infer's Topology-Aware Placement and Execution Optimizations into vLLM EPLB
- [Performance]: scheduler improvement to prevent KV-cache heavy requests from blocking others
- [Performance]: VLLM performance degradation when comparing with Tensor RT
- [Usage]: How to set different attention backend for prefill and decode phases?
- Docs
- Python not yet supported