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 supported2 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- qwen2-vl: AttributeError: '_OpNamespace' '_C' object has no attribute 'gelu_quick'
- [Bug]: Wrong "completion_tokens" counts in streaming usage
- [Misc]: How are quantized models loaded compared to non-quantized models?
- [Feature]: OpenAI o1-like Chain-of-thought (CoT) inference workflow
- [Usage]: Ray + vLLM OpenAI (offline) Batch Inference
- [Usage]:
- [Bugfix] Fix Phi3.5 mini and MoE LoRA inference
- [Kernel][Amd] Add fp8 kv cache support for rocm custom paged attention
- [Bugfix] Use heartbeats instead of health checks
- Support FP8 MoE for compressed-tensors
- Docs
- Python not yet supported