LiuXiaoxuanPKU / GACT-ICML
☆42Updated 2 years ago
Alternatives and similar repositories for GACT-ICML:
Users that are interested in GACT-ICML are comparing it to the libraries listed below
- This repository contains integer operators on GPUs for PyTorch.☆194Updated last year
- ☆137Updated 7 months ago
- ☆72Updated 3 years ago
- 16-fold memory access reduction with nearly no loss☆81Updated 3 weeks ago
- Code Repository of Evaluating Quantized Large Language Models☆117Updated 6 months ago
- ☆52Updated 11 months ago
- ☆52Updated 11 months ago
- PyTorch bindings for CUTLASS grouped GEMM.☆73Updated 4 months ago
- ☆27Updated 11 months ago
- code for the paper "A Statistical Framework for Low-bitwidth Training of Deep Neural Networks"☆27Updated 4 years ago
- pytorch-profiler☆51Updated last year
- Repository for artifact evaluation of ASPLOS 2023 paper "SparseTIR: Composable Abstractions for Sparse Compilation in Deep Learning"☆24Updated 2 years ago
- ☆39Updated 7 months ago
- ☆100Updated 6 months ago
- ☆24Updated 4 months ago
- Code for the NeurIPS 2022 paper "Optimal Brain Compression: A Framework for Accurate Post-Training Quantization and Pruning".☆113Updated last year
- The official PyTorch implementation of the NeurIPS2022 (spotlight) paper, Outlier Suppression: Pushing the Limit of Low-bit Transformer L…☆48Updated 2 years ago
- AFPQ code implementation☆20Updated last year
- ☆64Updated last month
- [IJCAI2023] An automated parallel training system that combines the advantages from both data and model parallelism. If you have any inte…☆51Updated last year
- PyTorch extension for emulating FP8 data formats on standard FP32 Xeon/GPU hardware.☆107Updated 3 months ago
- nnScaler: Compiling DNN models for Parallel Training☆101Updated last month
- Code for ICML 2021 submission☆35Updated 3 years ago
- ☆18Updated last year
- BitPack is a practical tool to efficiently save ultra-low precision/mixed-precision quantized models.☆51Updated 2 years ago
- Odysseus: Playground of LLM Sequence Parallelism☆66Updated 9 months ago
- ☆157Updated last year
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆256Updated 3 months ago
- (NeurIPS 2022) Automatically finding good model-parallel strategies, especially for complex models and clusters.☆38Updated 2 years ago
- Fast Hadamard transform in CUDA, with a PyTorch interface☆151Updated 9 months ago