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
- [ROCm][Perf] Defer GDN spec decode state stores in the Triton MTP kernel
- [MRV2] Stage-local eager DBO with pipeline parallelism
- [Dependency] Upgrade numba to 0.68.1
- [ROCm][Qwen4Exp][DeepSeek-V4.1] Add per_token PLE/Engram lookup mode
- [MRV2][DBO] Compose eager PCP partitions with microbatches
- [MRV2][DBO] Select eager microbatch counts within a fixed capacity
- [MRV2][DBO] Add stage-local FULL decode graphs for pipeline parallelism
- [RFC]: Large-page KV cache allocator: one KV cache group per spec
- [Bug]: Accuracy loss with NIXL EP and per-tensor FP8
- [Bugfix][EPLB] Start the async rearrangement interval after the last layer commits
- Docs
- Python not yet supported