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 supported3 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Usage]: Poor Successful requests with Llama 3.1 405-FP8 in 8xH100 SXM5
- [Bug]: KeyError: 'layers.0.self_attn.qkv_proj.weight' when using mistral or phi
- [Installation]: error: identifier "__builtin_dynamic_object_size" is undefined
- [Feature]: Support for predicted outputs
- [Usage]: how can i get all logits of token?
- [Bug]: AMD GPU tp>1 模型上线卡住
- [Usage]: Error executing method determine_num_available_blocks. This might cause deadlock in distributed execution.
- [Bug]: FlashInfer throws error in nightly: Please set `use_tensor_cores=True` in BatchDecodeWithPagedKVCacheWrapper for group size 3
- [Installation]: VLLM does not support TPU v5p-16 (Multi-Host) with Ray Cluster
- [Usage]: Engine iteration timed out. (during using qwen2-vl-7b)
- Docs
- Python not yet supported