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 supported60 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Feature]: [MRV2][DBO] Scoped eager decode overlap for hybrid attention/recurrent MoE models
- [Performance]: Evaluate SM90 TP2 mHC boundary fusion under rotating weights
- [Perf][DSA] Share the prefill indexer's logits schedule across layers on SM100
- WIP
- [Benchmark] Separate native and custom activation paths
- [ROCm][Perf] Muse Spark: MXFP4 MoE on native routes and column-sharded at TP prefill, via AITER's two-stage API
- [Kernel][MoE] Add HPC-Ops MoE backend for SM120 (FP8 and MXFP4)
- [Bugfix] Compute NIXL EP per-tensor FP8 scale over valid rows only
- [Perf][Multimodal] Add `mm_tensor_ipc="cuda_ipc_pool"`: TP-aware GPU transport
- [CI][XPU] Lower memory utilization for compile correctness embedding …
- Docs
- Python not yet supported