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 supported62 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Security] Apply media byte limits to Rust frontend
- [Bugfix] Fall back to one pipeline stage when Triton decode attention exceeds shared memory
- [Bug]: GB10 (sm_121), NVFP4 + Marlin MoE + MTP: engine dies daily ~2k sequential short requests into a batch job (Xid 13+31 write to VA 0x0; Xid 13+43 at a fixed address on all SMs)
- [Bugfix] Apply LM-head bias in native Moondream3 and PhiMoE models
- [Fusion][Perf] Extend QuantizedActivation contract with get_input_quant_scale and maybe_fused_norm_quant
- [Bugfix] Roll back failed file-plugin imports
- [Core] Add defer mode for long prefills
- [Bugfix][Spec Decode] Warn on near-zero draft acceptance
- [Perf][RL] Batch incremental routed-expert transport
- [Misc][Attention] Warn when Triton attention is auto-selected on pre-…
- Docs
- Python not yet supported