ThisisBillhe

Can't open port 80 for web service

3

nginx: [emerg] bind() to 0.0.0.0:80 failed (13: Permission denied) but i am using the root user

是否支持BGEMM？

3

请问二值化的linear和matmul操作是否支持？

When I use ImageNet Val dataset to calibrate 4bit resnet18, I got a result of 8.77%, while the distilled data could reach 20%. So original data is not perfect to...

### Brief Description the elementwise template [here](https://github.com/Oneflow-Inc/oneflow/blob/master/oneflow/core/cuda/elementwise.cuh) seems to be slow in my case. Specifically, I implement a dequantization kernel: ```cpp template struct DequantFunctor { __device__ __host__ __forceinline__ T operator()(int...

How to reproduce result of FID 3.60 over LDM-4-G on ImageNet?

4

1. Should I use cin256-v2.yaml for LDM-4? 2. The paper only mentioned scale=1.5 and step=250 but didn't mention the eta for this result. I tried using eta=0 (IS=115, FID=5.04) and...

请问什么时候可以支持INT4推理？

1

在rk3588这一代的npu介绍里是有INT4的支持，请问现在是否有接口使用？或者未来什么时候会有支持？

the generation speed of opensora-1.1 is much slower than 1.0 version with similar quatlity

3

I tested on V100 32G, without flashattention. For 1.0, the generation speed can reach 3.4 it/s. For 1.1 version, it's 1.5 it/s. What operation slow down that speed?

Thanks for your excellent work! However, I got some problems running this example 1) Do I have to install TensorRT in order to run this example? If so, where can...

Runtime error in I3D model

17

Hi! Thanks for your work. I have this error when running demo.py: RuntimeError: forward() is missing value for argument 'x'. Declaration: forward(__torch__.src.i3dpt_jit.I3D self, Tensor x, bool rescale=False, bool resize=False, bool...