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 supported31 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- Fix fp8 cache gather block table bounds
- [Bugfix] cumem: stream-sync before unmap and at wake_up exit to prevent CUDART illegal-memory crash
- [Core] Priority-based preemption at max_num_seqs
- [ROCm][Kernel] Extend skinny gemm N=5 to N=8 cases on GFX12 (RDNA4) using SWMMAC optimization
- [Core] Priority scheduling: preempt running requests for higher-priority waiting requests at max_num_seqs
- [Bugfix] cumem: validate VA/handle invariants and recover from wake-time cuMemMap failures
- [Bugfix][Frontend] Handle constrained Harmony output without recipient
- [Attention] Porting MLARoPEKVCacheCatFusionPass to manual fusion
- [Bugfix][KV Cache] Fix hybrid block size alignment across heterogeneous TP
- draft wip mamba mtp state replay
- Docs
- Python not yet supported