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 supported43 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Perf] Replace cudaMemsetAsync with in-kernel cleanup for persistent_topk
- fix(spec-decode): resync thinking state before target logits in rejec…
- [Kernel] Fuse logit softcapping into a single Triton kernel
- [Bug]: gemma4 31B MTP Avg Draft acceptance rate: 0.2%
- [Bugfix][Model] Fix DeepSeek V4 scale_fmt default for non-canonical quant configs
- [Bugfix] find_loaded_library: skip stub libraries and continue iterating
- [KV Offload] Expose SimpleCPU offload metrics
- [Doc] Add JarvisLabs deployment guide
- [Attention][MLA] Add Triton-fused TurboQuant decode backend
- [Feature]: Polymorphic buffer management for V1 worker (CPU/GPU staged tensors, lower hot-path overhead)
- Docs
- Python not yet supported