-
## Motivation #
There is significant interest in vLLM supporting encoder/decoder models. Issues #187 and #180 , for example, request encoder/decoder model support. As a result encoder/decoder supp…
-
## Description
Hello, I found that evaluate_mil() cannot generate attention heatmaps for 'clam_mb' model while train_mil() with the same parameters can generate heatmaps for 'clam_mb' without a probl…
-
### Describe the bug
the transformer model introduced in SD3 expects the below parameters (transformer_sd3.py). there are two missing parameters that remain undefined in the SD3ControlNetModel class …
-
`---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
[](https://localhost:8080/#) in ()
19
…
-
### System Info
### System Info
Hardware: Amazon Linux EC2 Instance.
8 NVIDIA A10G (23 GB)
```
Python 3.10.14
CUDA Version: 12.3
accelerate==0.34.2
bitsandbytes==0.44.1
nvidia-cublas-cu12…
-
Used to be just Scheduler but I converted that to widget and it worked
After the latest ComfyUI update, …
-
In line 221 of file .\models\modeling_showo.py, probably the shape of attention (L+1,L+1) instead of (1,1,L+1,L+1) mask is changed while iteration of generating new words. It can be fixed by adding c…
-
准备好环境后sophon-demo/sample/StableDiffusionXL/scripts，执行./get_unet_bmodel.sh里的get_unet_bmodel.sh时，生成mlir成功了，但mlir到bmodel时出错了，具体报错信息如下：
[Running]: tpuc-opt unet_base_bm1684x_bf16_final.mlir --codegen="mo…
-
With https://github.com/tenstorrent/tt-metal/pull/12309, causal SDPA no longer accepts an attention mask. It instead generates its own causal mask. The PR only removed the attention mask from calls to…
-
Gettin below error:
Can someboday help?
I am running python i2v_test.py
with torch.no_grad(), torch.cuda.amp.autocast():
Traceback (most recent call last):
File "/home/ec2-user/SageMaker/D…