-
不知道大佬您是否完成了pytorch框架的源码，如果可以的话能否让我学习参考一下，超级感谢您！528193010@qq.com
-
I used mtq.INT8_default_CFG as recommended for CNN networks (mtq.quantize(model, config, forward_loop). My initial model ran at 80FPS after quantization it dropped to 40FPS? I checked the model struct…
-
### 🐛 Describe the bug
Specifically, if we try to compile a float8 version of a FFN expert (`MixtralBlockSparseTop2MLP`), we see shape errors
Script (requires torchao and transformers):
```py…
-
Thanks to your help - I have added custom losses, special initialization and a bunch of other things as extensions.
I am now trying to mess with the sentence classification model itself. It is a li…
-
Thanks for the great work！But when I try to reproduce I get an error when running the py file. Check the error report. The error occurs in the load_model statement. It should be caused by the incompat…
-
I can successfully run fcos_demo.py I can successfully run fcos_demo.py, but when I try to run webcam.py, I get the error:
Traceback (most recent call last):
File "webcam.py", line 80, in
…
-
### 🐛 Describe the bug
When trying to run distributed/run_dist_inference.sh . It has below error.
[rank0]:[rank0]: model = _load_model(builder_args)
[rank0]:[rank0]: File "/scratch/grace/torc…
-
### 🐛 Describe the bug
**🐛 Bug**
- cuDNN error on Torch 1.6.0 with CUDA 10.1 when running on a 1080Ti with 512.15 Nvidia drivers.
- cuDNN error on Torch 1.11.0 with CUDA 11.3 when running on a 1080…
-
## The bug
Importing torch raises `undefined symbol: iJIT_NotifyEvent` from `torch/lib/libtorch_cpu.so: ` when pytorch and MKL 2024.1+ are installed together. Downgrading MKL to 2024.0.0 resolves it.…
-
hi i want to build a pytorch version base on a pytorch version mask-rcnn like this https://github.com/facebookresearch/maskrcnn-benchmark/tree/main/maskrcnn_benchmark
could you give me some advic…