Qualcomm-AI-research / FP8-quantization
☆122Updated 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
- PyTorch emulation library for Microscaling (MX)-compatible data formats☆163Updated last month
- This repository contains integer operators on GPUs for PyTorch.☆183Updated last year
- ☆40Updated 7 months ago
- ☆214Updated 2 years ago
- ☆195Updated 3 years ago
- 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
- Official implementation of the EMNLP23 paper: Outlier Suppression+: Accurate quantization of large language models by equivalent and opti…☆42Updated last year
- ☆156Updated last year
- ☆131Updated 3 months ago
- ☆167Updated 4 months ago
- List of papers related to Vision Transformers quantization and hardware acceleration in recent AI conferences and journals.☆54Updated 5 months ago
- ☆68Updated 2 years ago
- Code for the NeurIPS 2022 paper "Optimal Brain Compression: A Framework for Accurate Post-Training Quantization and Pruning".☆104Updated last year
- llama INT4 cuda inference with AWQ☆48Updated 4 months ago
- Code Repository of Evaluating Quantized Large Language Models☆104Updated 2 months ago
- A standalone GEMM kernel for fp16 activation and quantized weight, extracted from FasterTransformer☆85Updated 8 months ago
- A collection of research papers on efficient training of DNNs☆68Updated 2 years ago
- ☆80Updated last year
- Fast Hadamard transform in CUDA, with a PyTorch interface☆111Updated 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
- [ICLR 2022 Oral] F8Net: Fixed-Point 8-bit Only Multiplication for Network Quantization☆95Updated 2 years ago
- SparseTIR: Sparse Tensor Compiler for Deep Learning☆131Updated last year
- High-speed GEMV kernels, at most 2.7x speedup compared to pytorch baseline.☆90Updated 4 months ago
- Simple and fast low-bit matmul kernels in CUDA / Triton☆143Updated this week
- The official PyTorch implementation of the ICLR2022 paper, QDrop: Randomly Dropping Quantization for Extremely Low-bit Post-Training Quan…☆113Updated last year
- ☆80Updated 7 months 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
- QQQ is an innovative and hardware-optimized W4A8 quantization solution for LLMs.☆87Updated last month