-
```
Traceback (most recent call last):
File "/data/anaconda3/envs/torch/lib/python3.11/site-packages/streamlit/runtime/scriptrunner/exec_code.py", line 88, in exec_func_with_error_handling
re…
-
**Describe the bug**
I discovered the bug while testing because I wanted to try using the `dataflow` CB instead of `intermed`.
There are no issues when using bfloat16 tensors.
However, when using…
-
### Please describe your question
当我在尝试调用normal.py中的def normal_tensor_float(mean, std, *, generator=None):方法时,我采用了下面的方式:
```
mean = torch.randn(3, 4, device='cuda')
std = 1.5
result = normal_…
-
Using the latest transformers and sentence-transformers, on a multi-gpu system.
When I try to run this, the results are correct:
device=torch.device('cuda:0')
model=SentenceTransformer('danielef…
-
If I try to train a model with 7 stems for example, I get:
RuntimeError: The size of tensor a (2) must match the size of tensor b (7) at non-singleton dimension 1
-
With the recent advent of large models (take Llama 3.1 405b, for example!), distributed inference support is a must! We currently support naive device mapping, which works by allowing a combination of…
-
1. It seems the batch dimension will be disappeared after _upad_input function (this function is usually copied from transformers.models.mistral.modeling_mistral.MistralFlashAttention2._upad_input). T…
-
**Describe the bug**
当使用零样本克隆声音的时候,在运行如下命令时:
`output = cosyvoice.inference_zero_shot(temp_text, sound_clone_text, prompt_speech_16k)`
经常会出现这样的报错信息:`RuntimeError: The size of tensor a (5002) must ma…
-
I use the following script to export to ONNX
```
class ModelArgs:
hidden_dims: List[int] = field(default_factory=lambda: [128]*3)
n_downsample: int = 2
mixed_precision: bool = True
…
-
It will be great to have a few routines to compute tensor products.
We can do that with Enzyme.jl and add a backend for it in ADNLPModels.jl.