-
## Proposed refactoring or deprecation
Update the imports in the Lightning Quantization callback to `torch.ao.quantization`
### Motivation
Quantization in PyTorch 1.10 is moving under the…
-
Annoying to login to AWS to do it manually. Also should return status for the SQS queue.
-
如题,CPU可运行,NPU报错如下:
> [I 1/ 1 2:17:25.165 ...le-Lite/lite/core/optimizer/optimizer.cc:104 ApplyPasses] == Running pass: xpu_memory_optimize_pass
[I 1/ 1 2:17:25.165 ...le-Lite/lite/core/optimiz…
-
TensorRT supports two ways to build a quantization engine:
- PTQ with calibration or dynamic range API defined by the user manually
- Explicit quantization with Q/DQ ONNX model
The NNI speedup …
-
### Description
im in ubuntu 22.04 LTS (GNU/Linux 5.15.0-39-generic x86_64), docker Docker version 20.10.14, build a224086349 and python3 3.10.4-0ubuntu2
run lsusb with the result Bus 001 Device 0…
-
这个运行的顺序是怎么样的?应该以怎么样顺序运行
-
### Description
I'm trying to run the movenet_pose_estimation.py example.
It fails saying the tflite file is missing and yes it is.
I ran the bash command to get the files for movenet pose est…
-
**System information**
- OS Platform and Distribution (Linux Ubuntu 18.04):
- TensorFlow installed from (source or binary): binary
- TensorFlow version (or github SHA if from source): TF 2.3.0
…
-
We should move the non distributed examples into the //examples folder, including the ptq example and maybe the benchmark example.
We should then move trtorchc into //cpp/api/bin or move the api dir…
-
### 1. System information
- OS Platform and Distribution (e.g., Linux Ubuntu 16.04): platform agnostic
- TensorFlow installation (pip package or built from source): when MLIR-based post-training …