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
- [CI/Build] Skip DeepEP low-latency tests on B200 until the NVSHMEM fix
- [Perf] Tune cooperative TopK for SM107 + refine SM90/SM100F
- [Perf][MoE] Select full-warp top-k rows with redux.sync and keep selections in registers (SM80+)
- [ROCm][Attention] Accelerate ROCm Prefill Attention with FP8 Triton Kernels
- [Bugfix][KV Connector] Synchronize engine IDs across PCP ranks
- [Bugfix][Gemma4] Wire Gemma-4 MoE layers into EPLB
- [Performance]: Avoid dense initial-state materialization in Mamba2 continued prefill
- [Perf][Mamba] Avoid initial-state snapshots for single-sequence Mamba2 prefill
- [Bug]: LoRA + Gemma4 MTP speculative decoding crashes at startup — draft pre_projection shape mismatch
- [Frontend] Build and serialize logprob responses in pydantic-core
- Docs
- Python not yet supported