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 supported61 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [KV Connector] Preserve divergent hybrid hits with mixed connectors
- [Bugfix][Distributed] Enable expert parallelism in test_expert_parallel
- [Bugfix][ROCm] Let ROCM_ATTN share the BLHNC KV cache layout
- [Perf][ROCm][GLM-5.3-Flash] Default to breakable CUDA graphs on ROCm
- [Perf][ROCm][GLM-5.3-Flash] Defer KDA spec decode state writes
- [Perf][ROCm][GLM-5.3-Flash] Gluon KDA spec decode kernel for gfx950
- [ROCm][Kimi-K3] Enable encoder graph capture for Kimi-K3 Vision Tower
- [Bugfix] Declare Qwen GDN QKV input mutations
- [Feature][DSv4.1] Support arbitrary pipeline stage partitions
- [Bugfix][Core] Drop streaming updates that would overflow max_model_len
- Docs
- Python not yet supported