Model Quantization Benchmark
☆18Sep 30, 2025Updated 5 months ago
Alternatives and similar repositories for tpu-mq
Users that are interested in tpu-mq are comparing it to the libraries listed below
Sorting:
- ☆11Jan 10, 2025Updated last year
- [NeurIPS 2023] ShiftAddViT: Mixture of Multiplication Primitives Towards Efficient Vision Transformer☆30Dec 6, 2023Updated 2 years ago
- High Performance FP8 GEMM Kernels for SM89 and later GPUs.☆20Jan 24, 2025Updated last year
- PyTorch implementation of Near-Lossless Post-Training Quantization of Deep Neural Networks via a Piecewise Linear Approximation☆23Feb 17, 2020Updated 6 years ago
- IntLLaMA: A fast and light quantization solution for LLaMA☆18Jul 21, 2023Updated 2 years ago
- Pytorch implementation of RAPQ, IJCAI 2022☆23Jul 19, 2023Updated 2 years ago
- Domain-Specific Architecture Generator 2☆22Oct 2, 2022Updated 3 years ago
- A framework to compare low-bit integer and float-point formats☆66Feb 6, 2026Updated last month
- FastCache: Fast Caching for Diffusion Transformer Through Learnable Linear Approximation [Efficient ML Model]☆46Feb 17, 2026Updated 2 weeks ago
- Machine learning compiler based on MLIR for Sophgo TPU.☆872Feb 12, 2026Updated 3 weeks ago
- Offline Quantization Tools for Deploy.☆142Dec 28, 2023Updated 2 years ago
- [ECCV 2024] AdaLog: Post-Training Quantization for Vision Transformers with Adaptive Logarithm Quantizer☆42Dec 9, 2024Updated last year
- NART = NART is not A RunTime, a deep learning inference framework.☆37Mar 2, 2023Updated 3 years ago
- ☆37Jun 1, 2022Updated 3 years ago
- Inference of quantization aware trained networks using TensorRT☆83Jan 27, 2023Updated 3 years ago
- [CVPR 2025 Highlight] FIMA-Q: Post-Training Quantization for Vision Transformers by Fisher Information Matrix Approximation☆26Jun 16, 2025Updated 8 months ago
- using pvanet framework train mobilenet-v2 for objects detection, papaer: https://arxiv.org/abs/1611.08588☆13Feb 13, 2019Updated 7 years ago
- Flexible simulator for mixed precision and format simulation of LLMs and vision transformers.☆52Jul 10, 2023Updated 2 years ago
- An official PyTorch implementation of the paper "Distance-aware Quantization", ICCV 2021.☆48Nov 1, 2024Updated last year
- MoE-Visualizer is a tool designed to visualize the selection of experts in Mixture-of-Experts (MoE) models.☆16Apr 8, 2025Updated 11 months ago
- ☆11Aug 16, 2019Updated 6 years ago
- An Tensorflow.keras implementation of Same, Same But Different - Recovering Neural Network Quantization Error Through Weight Factorizatio…☆10Dec 18, 2019Updated 6 years ago
- LaTex template for ITMO style presentations☆10Jan 19, 2025Updated last year
- Integration test of Verilog AXI modules (https://github.com/alexforencich/verilog-axi) with LiteX.☆17Dec 19, 2022Updated 3 years ago
- ☆10Apr 10, 2019Updated 6 years ago
- Express DLA implementation for FPGA, revised based on NVDLA.☆11Oct 17, 2019Updated 6 years ago
- [CVPR 2022] AlignQ: Alignment Quantization with ADMM-based Correlation Preservation☆11Jan 6, 2023Updated 3 years ago
- KAF : Kolmogorov-Arnold Fourier Networks☆20Feb 19, 2025Updated last year
- The official code for [ECCV2020] "HALO: Hardware-aware Learning to Optimize"☆10Mar 22, 2023Updated 2 years ago
- ☆16Feb 23, 2025Updated last year
- This is a C++ implementation of cocoapi bbox evaluation code.☆11Dec 9, 2021Updated 4 years ago
- Training multi resolution GAN using MsCeleb datasets.☆12May 2, 2018Updated 7 years ago
- Training Quantized Neural Networks with a Full-precision Auxiliary Module☆13Jun 19, 2020Updated 5 years ago
- Write a cross_entropy function in pytorch to remove the abnormal nan value☆10Aug 22, 2019Updated 6 years ago
- Persistent dense gemm for Hopper in `CuTeDSL`☆15Aug 9, 2025Updated 6 months ago
- ☆11Apr 5, 2023Updated 2 years ago
- Python scripts for WIDER FACE Evaluation☆10May 25, 2019Updated 6 years ago
- ncnn export & infer mobileclip☆19Aug 18, 2025Updated 6 months ago
- A toolkit for developers to simplify the transformation of nn.Module instances. It's now corresponding to Pytorch.fx.☆13Apr 7, 2023Updated 2 years ago