-
### 🐛 Describe the bug
Hello PyTorch Team,
I am currently attempting to leverage Tensor Parallelism for inferencing the Llama-7b-chat-hf model. However, I've encountered a significant bottleneck…
-
Hi,
Thanks a lot for this awesome work! I am wondering whether there is a way to check the pruned but uncompressed model. Now when I save the model, they are already compressed, so I assume those p…
-
Hello, I'm always indebted to machina.
I implement QT-Opt for grasping tasks at PyBullet(https://github.com/bulletphysics/bullet3/blob/master/examples/pybullet/gym/pybullet_envs/baselines/train_kuk…
-
i downloaded `./GAMA/data/test/CompA-R-test.json' for gama_inf.py` for inference.
However, i got the error here:
[```tmp['scene_caption'] = i['caption']```](https://github.com/Sreyan88…
-
Hi all i am having some issues compiling
able to successfully `cmake . -B build`
but `cmake --build build --config RelWithDebInfo -j 16` results in multiple errors
` rs\admin\Desktop\nstantNerf\…
-
I'm attempting to implement ViTGaze, but I've encountered an issue with a specific line of code. Upon investigation, I noticed that it's not utilizing GPU resources at all and is freezing at this poin…
-
I am trying to use this model for classification of cifar10 in Google Colab. I was trying to load the model to study its layers so I cloned this repo and I am using it as follows:
```
from vision_…
-
Let's begin the planning for Find 2.0.
Some preliminary requirements:
1. Find 2.0 should unify the perf data structure of Findv1.0 and immediate mode
2. Find 2.0 should be able to accept the ui…
-
Problem: The model generates repetitive, nonsensical outputs like "Breis" regardless of the input provided. This happens even with different generation settings (e.g., temperature, top_k, top_p).
fro…
-
### Your current environment
```text
Collecting environment information...
PyTorch version: 2.3.1+cu121
Is debug build: False
CUDA used to build PyTorch: 12.1
ROCM used to build PyTorch: N/A
…