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
- fix(v1): skip full GC during EngineCore process exit
- [Doc] Add health probes to the AMD deployment example in k8s.md
- [Bug]: FastIncrementalDetokenizer leaks full prompt text into streamed output when prompt ends with an incomplete UTF-8 token
- [Bugfix] Prevent prompt text leaking into streamed output when prompt ends mid-UTF-8
- LoRA Triton kernel crashes with NVFP4 (modelopt_fp4) quantization - CUDA illegal memory access
- reasoning: null content when include_reasoning=False + json_schema response_format (introduced v0.23.1)
- [Metrics] Consolidate Prometheus histogram bucket defaults into a single module
- [Metrics] Add --custom-histogram-buckets to override histogram bucket families
- [Model][Quant] Fused WNA16 GEMM for tied quantized lm_head logits
- [Doc]: batch_invariance.md said "compute capability 9.0+" in v0.20.0–v0.22.0 while code already supported 8.0+ (fixed in v0.23.0)
- Docs
- Python not yet supported