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
- [Perf][GLM-5.3] Extend GLM low-latency BF16 GEMM table on SM103
- [Bugfix][Kernel] Use GegluTanh for GELU_TANH in the FLASHINFER_CUTLASS MoE backend
- [Hardware] Keep current_stream() in sync with torch.accelerator.set_stream
- [MRV2][DBO] Split eager decode steps for hybrid recurrent models
- [Perf][Kernel] Tune SM90 FP8 CUTLASS tiles for M in (128, 192] and (256, 448]
- [Model] Add Mistral Large 4
- [Feature][Structured Output] Support continued assistant prefixes
- [Spec Decode][MRV2] Extend speculator request lifecycle hooks
- [Bug]: thinking_token_budget never triggers for Mistral models that use [THINK] tokens (tokenizer_mode=mistral)
- [Bugfix][PP][Spec Decode] Relay Qwen3-MoE EAGLE3 aux hidden states over PP
- Docs
- Python not yet supported