IBM / qattnLinks
Efficient GPU kernels for mixed-precision Vision Transformers in Triton
☆13Updated last month
Alternatives and similar repositories for qattn
Users that are interested in qattn are comparing it to the libraries listed below
Sorting:
- [TMLR] Official PyTorch implementation of paper "Efficient Quantization-aware Training with Adaptive Coreset Selection"☆33Updated 10 months ago
- ☆43Updated last year
- ☆76Updated 2 years ago
- [CVPR 2023] PD-Quant: Post-Training Quantization Based on Prediction Difference Metric☆56Updated 2 years ago
- Post-training sparsity-aware quantization☆34Updated 2 years ago
- Official implementation of the EMNLP23 paper: Outlier Suppression+: Accurate quantization of large language models by equivalent and opti…☆46Updated last year
- [TMLR] Official PyTorch implementation of paper "Quantization Variation: A New Perspective on Training Transformers with Low-Bit Precisio…☆45Updated 9 months ago
- BitPack is a practical tool to efficiently save ultra-low precision/mixed-precision quantized models.☆54Updated 2 years ago
- ☆11Updated 5 months ago
- [NeurIPS 2023] ShiftAddViT: Mixture of Multiplication Primitives Towards Efficient Vision Transformer☆31Updated last year
- This is the pytorch implementation for the paper: Generalizable Mixed-Precision Quantization via Attribution Rank Preservation, which is…☆25Updated 3 years ago
- A collection of research papers on efficient training of DNNs☆70Updated 2 years ago
- LLM Inference with Microscaling Format☆23Updated 7 months ago
- [TCAD 2021] Block Convolution: Towards Memory-Efficient Inference of Large-Scale CNNs on FPGA☆17Updated 2 years ago
- ☆22Updated 7 months ago
- Quantization in the Jagged Loss Landscape of Vision Transformers☆13Updated last year
- ☆149Updated 2 years ago
- Flexible simulator for mixed precision and format simulation of LLMs and vision transformers.☆50Updated last year
- [CVPR'20] ZeroQ Mixed-Precision implementation (unofficial): A Novel Zero Shot Quantization Framework☆14Updated 4 years ago
- [ICLR 2022 Oral] F8Net: Fixed-Point 8-bit Only Multiplication for Network Quantization☆95Updated 3 years ago
- source code of the paper: Robust Quantization: One Model to Rule Them All☆40Updated 2 years ago
- PyTorch implementation of Towards Efficient Training for Neural Network Quantization☆15Updated 5 years ago
- ☆12Updated 2 years ago
- The official PyTorch implementation of the NeurIPS2022 (spotlight) paper, Outlier Suppression: Pushing the Limit of Low-bit Transformer L…☆47Updated 2 years ago
- FakeQuantize with Learned Step Size(LSQ+) as Observer in PyTorch☆34Updated 3 years ago
- [ECCV 2022] SuperTickets: Drawing Task-Agnostic Lottery Tickets from Supernets via Jointly Architecture Searching and Parameter Pruning☆20Updated 2 years ago
- ☆35Updated 2 years ago
- Official implementation of "Searching for Winograd-aware Quantized Networks" (MLSys'20)☆27Updated last year
- [ICML 2023] This project is the official implementation of our accepted ICML 2023 paper BiBench: Benchmarking and Analyzing Network Binar…☆56Updated last year
- It's All In the Teacher: Zero-Shot Quantization Brought Closer to the Teacher [CVPR 2022 Oral]☆29Updated 2 years ago