bobbych94
bobbych94
```python import json import trt_pose.coco import trt_pose.models import torch class InputReNormalization(torch.nn.Module): """ This defines "(input - [0.485, 0.456, 0.406]) / [0.229, 0.224, 0.225]" custom operation to conform to "Unit" normalized...
> @nanmi您是否设法运行 yolox-tiny 或 yolox-nano？ I haven't tried it, but please share it if you verify it☺
We do not need to export NMS. NMS is in the post-processing part
Or, do you have reference codes for other repositories that you recommend that apply DCA technology? Can you share them?
> 您好，感谢您的关注！ DCA几乎可以用于Hugging Face上发布的所有LLM。如果您发现特定模型具有挑战性，请随时提出问题。 > > 对于 CUDA 优化，我们正在积极致力于此，但与原始推理代码相比，此存储库中的代码不应存在明显的 GPU 内存或推理时间问题。 Thanks for replying to the message. I want to apply DCA, a super useful technology, under the CUDA framework....
有可能是计算图中算子太多导致的，这种情况该如何打开呢，您有什么建议吗
> Seems H20's cuda architecture is not recognized, can you specify the environment variable: > > ``` > export TORCH_CUDA_ARCH_LIST=9.0 > ``` not work, I have tried setting the environment...
> Hello! May I ask if you can share the steps to preproduce the steps? Do you mean building the model or building tensorrt_llm source code? If you could add...
> > Any recent updates regarding the support for DeepSeek MOE? > > deepseek MOE hopefully will be appear in main branch in next week, deepseek v2 (MLA+MOE) hopefully will...
> deepseek v1 is ready to go, should appear in main branch in early next week, v2 we are still tuning , we are targeting to get the close perf...