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 supported43 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Test] Add MoE dtype asserts for hidden states and logits
- [RFC]: `nccl-m2n` for sharding-aware weight transfer in vLLM RL
- [Bug]: Hybrid Mamba + KV connector: per-group prefix-hit divergence and vllm engine crashed
- [Bugfix][Model] Fix DiffusionGemma GGUF tied embedding loading
- [Bug][TurboQuant] Fast-path incorrectly triggers with continuation requests under prefix caching, losing cached prefix K/V
- [Bug]: DFlash+Qwen3.6-35B-A3B, invalid gpu kv cache usage, low decode speed
- [Bug]: InternLM2 models crash with IndexError in embedding layer on CPU backend (v0.23.0 regression from v0.22.1)
- [Bug]: persistent KV Cache memory not released after benchmark completion
- [Bug]: Unclean shutdown on DeepEP timeout during startup causes hung processes
- [SimpleCPUOffloadConnector]: Add KV Events
- Docs
- Python not yet supported