.github Add CI for Arm Linux (#2211) May 16, 2025 benchmarks Feat: Implementation of the DeepSeek blockwise quantization for fp8 t… May 13, 2025 docs Micro-benchmark inference (#1759) Mar 18, 2025 examples Update ruff version to 0.11.6 (#2103) ...
master 3Branches0Tags Code Folders and files Name Last commit message Last commit date Latest commit Jermmy add QSigmoid Jun 18, 2023 704857d·Jun 18, 2023 History 32 Commits .gitignore add note for PTQ and QAT Jun 30, 2022 LICENSE ...
git clone git@github.com:yhwang-hub/yolov7_quantization.git 2.Install dependencies pip install pytorch-quantization --extra-index-url https://pypi.ngc.nvidia.com 3.Prepare coco dataset .├── annotations │ ├── captions_train2017.json │ ├── captions_val2017.json │ ├── instan...
A pytorch implementation of dorefa quantization. Contribute to Jzz24/pytorch_quantization development by creating an account on GitHub.
Quantized CPU ops: https://github.com/pytorch/pytorch/tree/master/aten/src/ATen/native/quantized/cpu Tests for quantized tensors: https://github.com/pytorch/pytorch/blob/master/test/test_quantized_tensor.py Quantized modules: Modules:https://github.com/pytorch/pytorch/tree/master/torch/nn/qua...
A pytorch Quantization Toolkit. Contribute to leo-gan/quanto development by creating an account on GitHub.
git clone -b main https://github.com/nvidia/TensorRT TensorRT cd TensorRT git submodule update --init --recursive (Optional - if not using TensorRT container) Specify the TensorRT GA release build path If using the TensorRT OSS build container, TensorRT libraries are preinstalled under /usr/li...
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment Assignees ttyio Labels triaged Projects None yet Milestone No milestone Development No branches or pull requests 4 participants Footer © 2024 GitHub, Inc. Footer navigation Terms Privacy...
git clone https://github.com/pytorch/pytorch.git cd pytorch git submodule update --init --recursive pip install -e . 这里的-e参数指的是editable模式,使得在开发过程中可以即时看到对代码的修改。 按照以上步骤操作,您应该能够成功安装pytorch-quantization。如果在安装过程中遇到任何问题,请查阅相关文档或寻...
Today, we are excited to introduce [🤗 quanto](https://github.com/huggingface/quanto), a versatile pytorch quantization toolkit, that provides several unique features: - available in eager mode (works with non-traceable models) - quantized models can be placed on any device (including CUDA an...