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
- [Bug]: VLLM_USE_MODELSCOPE path conversion uses stale cache layout — multimodal processor loading crashes with HFValidationError
- [Bugfix][KV Offload] Keep direct caches topology-specific
- [Bugfix][Pooling] Clear V1 pooling state after preemption
- [Bug]: TensorizerLoader skips post-load weight processing
- [Bugfix][Parser] Preserve prose after tool calls
- [Bugfix][Pooling] Validate truncated Jina ranking prompts
- [RFC]: Add QoL improvements to profiler
- [Bugfix][EPLB] Reject unsafe dynamic weight updates
- [Bugfix] Reject prompt embeddings for BERT/RoBERTa models
- [Bugfix][Model] Fix Qwen3 MoE 1D input handling
- Docs
- Python not yet supported