-
### 🐛 Describe the bug
This failure found in the latest [ TorchInductor CPU Performance Dashboard](https://github.com/pytorch/pytorch/issues/93531) refresh test with below error log
SW info:
SW…
-
Hi, I was wondering if anyone could help how to convert and quantize SSD models on TF2 Object Detection Model Zoo.
It seems like there's a difference in converting to .tflite in TF1 and TF2. To t…
-
## ❓ Questions
Hi there, I'm currently trying to train htdemucs in a colab environment, with around 40GB of vram. I made a simple variant of the default experiment and I'm running using !dora run -…
-
Hi there,
I'm trying to replicate the PQT and QAT procedure by following the [Export Readme](https://github.com/NVIDIA-AI-IOT/cuDLA-samples/blob/main/export/README.md) step by step.
I can reproduc…
-
## Description
Yolov8m TensorRT QAT model is slower than PTQ model
## Environment
**TensorRT Version**:
8.4.1.5
**NVIDIA GPU**:
RTX2080
**NVIDIA Driver Version**:
**CUDA Versio…
-
We're currently trying to track the number of maps a modder user has helped achieve Ranked status over the years. It was brought up during internal discussions that these values should also be publicl…
-
## Description
I tried to run EfficientViT-SAM on a RTX 3090, but quantization to 8-bit gave severely distorted results. Unsure whether issue has to do with calibration code, or nature of quantiz…
-
### 🐛 Describe the bug
quantization QAT/PTQ accuracy test meets crash with [2024-02-25 nightly release](https://github.com/pytorch/pytorch/commit/53f5035912dc9736546a512713aeb60896d00027)
```
Trace…
-
Reference the method in [OpenVINO Stable Diffusion QAT example](https://github.com/huggingface/optimum-intel/blob/main/examples/openvino/stable-diffusion/train_text_to_image_qat.py) , the original sa…
-
I have `INT8` quantized a `BERT` model for binary text classification and am only getting a marginal improvement in speed over `FP16`.
I am using the `transformer-deploy` library that utilizes Tens…