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 supported36 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- Reject oversized media before fully downloading it
- [Bug] v0.27.0 engine permanently stalls after ~1 min idle on 4-node TP=4 (GB10/sm_121, aarch64): shm_broadcast writer starves, requests never reach scheduler
- [MoE] Refine FlashInfer one-sided All2All integration
- [CPU] Shard the MoE experts across NUMA nodes
- [ROCm][Perf] Kimi-K3 Remove prefill pipeline stall in chunk KDA
- [Bugfix][Benchmark] Check readiness before tokenizer init in rust vllm-bench
- [ROCm][K3] Dequantize the fp8 decode query for MLA backends without quant-query support - TRITON_MLA
- Remove NIXL reinstall step
- [Quantization] Implement FP8 block padding for unaligned cases
- [Bugfix][MRV2] Respect dynamic K=0 from scheduler in AutoRegressiveSpeculator
- Docs
- Python not yet supported