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]: Hidden States not working in Speculative Decode
- [Bugfix] Fix chunked prefill with model dtype float32 on Turing Devices
- [V1] Multiprocessing tensor parallel prototype
- [CI/Build] Update PyTorch to the 2.5.1 bugfix release
- [Performance]: Qwen2-VL-7B AWQ model performance
- [New Model]: 请问接下来有支持诸如GPT-SoVITS之类的语音生成大模型的计划吗?
- [Bug]: Function calling with Qwen & Streaming ('NoneType' object has no attribute 'get')
- [Neuron] Skip model attention head compatibility check with tensor pa…
- [Bug]: seq_group_metadata.encoder_seq_data.get_len() AttributeError: 'NoneType' object has no attribute 'get_len'
- [V1] Complete v1 sample and prompt logprobs support
- Docs
- Python not yet supported