Repository Issue Activity (beta)

#246 How to make stable TensorRT fp16 inference?

#233 支持 structured outputs 么

#235 下载模型文件完后 运行python app/hydit_app.py --no-enhance 提示缺少 ckpts/t2i/controlnet， ckpts/t2i/lora

#245 docker环境配置--load-4bit报错No package metadata was found for bitsandbytes

#244 执行export_onnx.py报错

#66 Questions about ROPE applied on MultiheadCrossAttention

#243 我好奇这个模型在腾讯游戏内部工作流运用的如何？

#234 Bug when setup tensorRT

#241 使用蒸馏模型lora训练模型结构不匹配

#237 希望增加中文说明

#240 fmha_plugins 的源代码可以提供一下吗？

#239 FileNotFoundError: Cannot find model checkpoint ./ckpts/t2i/model/pytorch_model_distill.pt after following README instructions

#182 cannot import name 'LlavaLlamaForCausalLM' from 'llava.model'

#236 Where is DialogBen(benchmark)?

#229 咨询全量8p训练时遇到的with open(f"{experiment_dir}/args.json", "w") as f: : [Errno 13] Permission denied: '/args.json'问题

#232 HunyuanDiT 比肩 FLUX.1吗

#205 是否有新的hunyuan要发布，flux.1很大也很强

#231 评价指标

#230 关于模型中CLIP的实现问题

#103 cuda12难道不能训练吗，非要cuda11？

#223 Will released Controlnet train code?

#224 `to_index_v2` not defined

#227 请问huggingface对应的Tencent-Hunyuan / IP-Adapter 下的ipadapter的模型权重所对应的base文件是hunyuanv1.0、v1.1还是v1.2？

#228 微调IP_adapter，请问如何生成对应的训练数据集？按照普通的全参微调生成的数据进行微调，报错。

#226 diffuser version support Ascend NPU!