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 supported29 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [SpecDecode] Add shortcut in rejection sampler for greedy sampling
- [Perf] Add A100 fused MoE tuned config for E=16,N=3072
- _update_request_as_session does not update max_tokens from StreamingUpdate
- [Core] CUDA Checkpoint/Restore — Phase 2: Engine/Executor/API Integration
- [Usage]: v0.18.0 nvidia/nemotron-colembed-vl-4b-v2 /embeddings 404
- Revert "[Bug][MoE] Fix TRTLLM NVFP4 Routing Kernel Precision" (#36725)
- [Feature] Use Fp8 Query for Triton Attention on ROCm
- [Bugfix][Model] Fix Eagle2.5-VL using ImageNet normalization instead of SigLIP2
- [Mamba] Speculative Decoding Mamba
- [compile] Add a fast serializer for aot save/load.
- Docs
- Python not yet supported