Qualcomm-AI-research / FP8-quantization
☆121Updated last year
Related projects ⓘ
Alternatives and complementary repositories for FP8-quantization
- PyTorch extension for emulating FP8 data formats on standard FP32 Xeon/GPU hardware.☆100Updated 11 months ago
- ☆192Updated 3 years ago
- PyTorch emulation library for Microscaling (MX)-compatible data formats☆162Updated last month
- ☆38Updated 7 months ago
- ☆214Updated 2 years ago
- This repository contains integer operators on GPUs for PyTorch.☆181Updated last year
- Official implementation of the EMNLP23 paper: Outlier Suppression+: Accurate quantization of large language models by equivalent and opti…☆41Updated last year
- The official PyTorch implementation of the NeurIPS2022 (spotlight) paper, Outlier Suppression: Pushing the Limit of Low-bit Transformer L…☆46Updated 2 years ago
- Improving Post Training Neural Quantization: Layer-wise Calibration and Integer Programming☆95Updated 3 years ago
- Code for the NeurIPS 2022 paper "Optimal Brain Compression: A Framework for Accurate Post-Training Quantization and Pruning".☆101Updated last year
- A standalone GEMM kernel for fp16 activation and quantized weight, extracted from FasterTransformer☆85Updated 8 months ago
- llama INT4 cuda inference with AWQ☆47Updated 4 months ago
- ☆130Updated 3 months ago
- ☆67Updated 2 years ago
- Code Repository of Evaluating Quantized Large Language Models☆103Updated 2 months ago
- ☆121Updated this week
- SparseTIR: Sparse Tensor Compiler for Deep Learning☆131Updated last year
- ☆79Updated 11 months ago
- [ICLR 2022 Oral] F8Net: Fixed-Point 8-bit Only Multiplication for Network Quantization☆95Updated 2 years ago
- Pytorch implementation of BRECQ, ICLR 2021☆250Updated 3 years ago
- Fast Hadamard transform in CUDA, with a PyTorch interface☆107Updated 5 months ago
- The official PyTorch implementation of the ICLR2022 paper, QDrop: Randomly Dropping Quantization for Extremely Low-bit Post-Training Quan…☆112Updated last year
- List of papers related to Vision Transformers quantization and hardware acceleration in recent AI conferences and journals.☆53Updated 5 months ago
- Code for the AAAI 2024 Oral paper "OWQ: Outlier-Aware Weight Quantization for Efficient Fine-Tuning and Inference of Large Language Model…☆53Updated 8 months ago
- QQQ is an innovative and hardware-optimized W4A8 quantization solution for LLMs.☆75Updated 3 weeks ago
- [ICML 2023] This project is the official implementation of our accepted ICML 2023 paper BiBench: Benchmarking and Analyzing Network Binar…☆54Updated 8 months ago
- ☆156Updated last year
- ☆78Updated 6 months ago
- BitPack is a practical tool to efficiently save ultra-low precision/mixed-precision quantized models.☆49Updated last year
- ☆162Updated 3 months ago