-
### Issue type
Bug
### Have you reproduced the bug with TensorFlow Nightly?
Yes
### Source
source
### TensorFlow version
tf 2.14.0
### Custom code
Yes
### OS platform and…
-
### Issue type
Bug
### Have you reproduced the bug with TensorFlow Nightly?
Yes
### Source
source
### TensorFlow version
tf 2.14.0
### Custom code
Yes
### OS platform and…
-
### Issue type
Bug
### Have you reproduced the bug with TensorFlow Nightly?
Yes
### Source
source
### TensorFlow version
tf 2.14.0
### Custom code
Yes
### OS platform and…
-
### Issue type
Bug
### Have you reproduced the bug with TensorFlow Nightly?
Yes
### Source
source
### TensorFlow version
tf 2.14.0
### Custom code
Yes
### OS platform and…
-
### Issue type
Bug
### Have you reproduced the bug with TensorFlow Nightly?
Yes
### Source
source
### TensorFlow version
tf 2.14.0
### Custom code
Yes
### OS platform and…
-
### Issue type
Bug
### Have you reproduced the bug with TensorFlow Nightly?
Yes
### Source
source
### TensorFlow version
tf 2.14.0
### Custom code
Yes
### OS platform and…
-
**🚀 Feature**
CUDA-Graph is introduced in CUDA-10.1 to reduce kernel launch overhead. CUDA-Graph matches current NNFusion's design, so it could be easily integrated to cuda_codegen to improve perfo…
-
Hi,
I found that the unpad_input function makes the cuda graph capture fail if we have key_attention_mask.
https://github.com/HazyResearch/flash-attention/blob/72ad03eaa661f6bf3a14c855316c27fbab4f…
-
### 🐛 Describe the bug
Hi,
Dynamo can capture the stream and its runtime API with this PR https://github.com/pytorch/pytorch/pull/93808.
Stream APIs can be traced into the FX graph and no graph…
-
Hi, I tried to get yolov8 INT8 engine file by following steps from [https://github.com/marcoslucianops/DeepStream-Yolo/blob/master/docs/INT8Calibration.md](url).
However, I getting this error "ERROR:…