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][P1]: docker image / cache reuse between CI and release pipelines
- [Feature]: Optionally Return LogSumExp in Attention
- [docker] kv_connectors (lmcache) not installed on arm64 release images
- [Bug]: compilation_config.backend="eager" doesn't work aot mode (yet).
- [Usage]: Qwen3-30B-A3B-NVFP4 fails on Dell Pro Max GB10 with "no kernel image is available for execution on the device"
- [Draft] [RFC]: vLLM + UCC Backend
- [Feature]: Support NVIDIA ModelOpt FP8 PTQ variants (FP8_PER_CHANNEL_PER_TOKEN / FP8_PB_WO) in vLLM
- [Feature]: The issue of being unable to achieve streaming output in function call inference
- [Performance]: Why Does Latency Remain Unchanged in vLLM 0.11.0 When Input Token Count Decreases for qwen3-vl-30b-a3b?
- [Bug]: GLM4-MoE AssertionError with --all2all-backend pplx (dtype mismatch)
- Docs
- Python not yet supported