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 supported51 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Kernel][Perf] Support DSpark K=8 in fused GDN MTP decode
- [Benchmark] Add asyncio-based multi_turn benchmark v2 to fix deadlock
- [XPU] Add VLLM_XPU_DEVICE_OFFSET to place a worker on a non-zero card without masking
- [Bugfix][KV Connector] Mooncake: heterogeneous-TP support for hybrid GDN/Mamba models
- [Bugfix] Separate target and draft scheduling budgets
- [Perf][MoE] Share FlashInfer B12x MoE workspaces across layers
- [Core] Make sleep a pure memory-state transition
- [Perf][Spec Decode] Fuse target temperature in rejection sampler
- [Parser] Move structural-tag capabilities into parser engines
- [Bugfix][Spec Decode] Fix eagle draft sharing with a quantized lm_head
- Docs
- Python not yet supported