MIT License
Published by Tlntin 7 months ago
Full Changelog: https://github.com/Tlntin/Qwen-TensorRT-LLM/compare/v0.6.1...v0.7.0
Full Changelog: https://github.com/Tlntin/Qwen-TensorRT-LLM/compare/v0.5.0...v0.6.1
Published by Tlntin 9 months ago
修复了一些已知问题,更新triton部署文件,新增qwen-vl支持。
Published by Tlntin 11 months ago
qwen/Readme.md
NVIDIA TensorRT Hackathon 2023相关的所有代码
4 bits quantization of LLaMA using GPTQ
⚡ Build your chatbot within minutes on your favorite device; offer SOTA compression techniques fo...
Tools for simple inference testing using TensorRT, CUDA and OpenVINO CPU/GPU and CPU providers. S...
【大模型】3小时完全从0训练一个仅有26M的小参数GPT,最低仅需2G显卡即可推理训练!
Efficient, scalable and enterprise-grade CPU/GPU inference server for 🤗 Hugging Face transformer ...
Panda项目是于2023年5月启动的开源海外中文大语言模型项目,致力于大模型时代探索整个技术栈,旨在推动中文自然语言处理领域的创新和合作。