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 supported49 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Core][MoE] Add host-bank primitives for expert-granular MoE offload
- [Bugfix] Handle MoE padding sentinel in FlashInfer b12x experts
- [ROCm][Perf] Reach the fused QSA pre-indexer from the AMD path
- [Perf][KV Connector][Mooncake] Pack hybrid/MLA KV into coalesced transfer regions
- Repro/qwen35 4b dflash
- [Core][Logging] Fix JSON logging process decoration
- [Bugfix][Spec Decode] Raise a DFlash draft's max_position_embeddings to the target's max_model_len
- Add routed-expert prefix omission for AuxOutput
- [AuxOutput] Add Mooncake backend with keys-only R3 output
- [Bugfix][Responses API] Execute parallel built-in tool calls
- Docs
- Python not yet supported