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 supported31 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Spec Decode] Avoid materializing target probabilities in rejection sampling
- perf(moe): add tuned fused_moe FP8 config for RTX 5090
- [Bugfix] Fix int32 overflow in concat_mla_q flat warp index
- [Security] Add configurable input size bounds for DoS mitigation
- [Kernel] Resurrect rotted gather-cache OOB test + defensive block-table bound-checks
- [Core][RFC #34303] Add CuMemTagBackend for tag-selective offload on top of #44074
- [BugFix] Don't strand parked async-KV-load requests behind an unschedulable queue head
- [Bug]: vLLM crashes during generation with LMCacheMPConnector on Qwen3.6/Qwen3.5 hybrid model: AssertionError "External KV connector is not verified yet"
- fix: remove extraneous 'messages' argument in DeepseekV4Renderer chat template call (closes #44949)
- fix: correct operator precedence in use_existing_torch.py (closes #42363)
- Docs
- Python not yet supported