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 supported62 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bugfix][Core] Redo prompt logprobs for requests resumed after reset_prefix_cache
- [Docs][KV Connector] Document NIXL KV connector metrics aggregation semantics
- [Bugfix] Stop engines before API servers so --shutdown-timeout drains with --api-server-count > 1
- [XPU][Platform] Handle nodes with both CUDA and XPU drivers active
- [RFC]: Early KV transfer for direct Mooncake P/D
- [ROCm][Perf][Qwen3.8] Add dense mono decode for Qwen3.8-27B on MI355X.
- [Docs][Model] Add Qwen2.5-Coder-1.5B-Instruct to batch invariance tested models
- [Perf] Lower FlashInfer CuTeDSL BF16 GEMM to aten mm above 32 tokens
- [Bugfix][KV Connector][NIXL] Support heterogeneous P/D TP for mixed MLA models
- [Bugfix] Reserve construction-time scratch across workspace slots
- Docs
- Python not yet supported