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 supported49 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: Qwen3.5 GDN CUDA kernels promote BF16 Q/K normalization to FP32
- [Bug]: persistent_topk silently drops top-k candidates when many values share a coarse histogram bin
- [Bug]: [KV-Transfer] Scheduler crashes due to duplicate `recving` completion events in `MultiConnector` across scheduler steps
- [Bug]: DeepSeek-V4-Flash-0731 shows severe 1M KV concurrency regression on B300 (27.08x preview vs 7.73x 0731 + DSpark)
- [Quark] Remove quark-specific silent online quantization
- [Online quantization] Support activation quant key override
- [Tests][Parser] Add unit tests for tool-call parser metrics
- Copy CPU shared-memory tails at their exact length
- [BugFix] Clamp Mooncake store token_len to hash coverage under MTP/async scheduling
- [Bug]: Optional usage telemetry (py-cpuinfo) can kill engine startup in a forked worker
- Docs
- Python not yet supported