-
**What API design would you like to have changed or added to the library? Why?**
Is it possible to allow setting every tensor attribute of scheduler to cuda device?
In https://github.com/huggingface…
-
Hello.
I am trying to edit cook_spinach scene of neural_3d dataset using pretrained checkpoints. But I am getting tensor shape mismatch error [snap attached].
 with model-control-mode=explicit. The server seems to hold onto physical RAM after inference requests…
-
Hello, I used the training scripts to train the qwen version of longVU but unfortunately I don't manage to load the checkpoints with the eval scripts.
This is the error that I am getting:
File "…
-
when I used this command to run the bear dataset used the image that you processed:
ns-train gaussctrl --load-checkpoint unedited_models/bear/splatfacto/2024-11-04_182528/nerfstudio_models/step-0…
-
### 问题确认 Search before asking
- [X] 我已经搜索过问题，但是没有找到解答。I have searched the question and found no related answer.
### 请提出你的问题 Please ask your question
配置文件如下
```
use_gpu: true
use_xpu: false
use…
-
### Description of the bug:
Bad StatusOr access: FAILED_PRECONDITION: DNN library initialization failed. Look at the errors above for more details.
While executing %nonzero : [num_users=2] = call…
-
Pytorch 2.3 is introducing unsigned integer dtypes like `uint16`, `uint32` and `uint64` in https://github.com/pytorch/pytorch/pull/116594.
Quoting Ed:
> The dtypes are very useless right now (not…
-
### 🐛 Describe the bug
Hi torch distributed team!
As we discussed in PTC, we found functional collectives are 34%~67% slower than c10d collectives due to the heavy CPU overhead.
To be specific,…
-
您好，我正在把lightGlue模型移植到RK3588板端，目前使用rknnlite2的Python脚本在板端推理符合预期。但是使用c++代码推理同样的模型时，直接得到的输出结果与rknnlite2的Python脚本结果差异较大。
以下是我的详细操作：
1、从onnx转换成rknn模型后，输入输出维度如下所示：有四个输入，一个输出。
转换rknn模型时，设置了QUANTIZE_ON = …