mit-han-lab / pruning-sparsity-publications
☆20Updated last year
Related projects: ⓘ
- ☆37Updated 2 months ago
- ☆134Updated last year
- [ACL 2024] A novel QAT with Self-Distillation framework to enhance ultra low-bit LLMs.☆69Updated 4 months ago
- IntLLaMA: A fast and light quantization solution for LLaMA☆18Updated last year
- A standalone GEMM kernel for fp16 activation and quantized weight, extracted from FasterTransformer☆82Updated 6 months ago
- Standalone Flash Attention v2 kernel without libtorch dependency☆93Updated last week
- llama INT4 cuda inference with AWQ☆46Updated 2 months ago
- ☆113Updated last year
- [ICML 2023] This project is the official implementation of our accepted ICML 2023 paper BiBench: Benchmarking and Analyzing Network Binar…☆54Updated 6 months ago
- GPTQ inference TVM kernel☆35Updated 4 months ago
- Memory Optimizations for Deep Learning (ICML 2023)☆58Updated 6 months ago
- ☆67Updated last week
- TiledCUDA is a highly efficient kernel template library designed to elevate CUDA C’s level of abstraction for processing tiles.☆114Updated last week
- Odysseus: Playground of LLM Sequence Parallelism☆50Updated 3 months ago
- ☆29Updated 4 months ago
- GPU operators for sparse tensor operations☆27Updated 6 months ago
- The official PyTorch implementation of the NeurIPS2022 (spotlight) paper, Outlier Suppression: Pushing the Limit of Low-bit Transformer L…☆46Updated last year
- ☆186Updated 2 years ago
- flash attention tutorial written in python, triton, cuda, cutlass☆159Updated 3 months ago
- [ICML 2022] "Coarsening the Granularity: Towards Structurally Sparse Lottery Tickets" by Tianlong Chen, Xuxi Chen, Xiaolong Ma, Yanzhi Wa…☆30Updated last year
- High-speed GEMV kernels, at most 2.7x speedup compared to pytorch baseline.☆81Updated 2 months ago
- Penn CIS 5650 (GPU Programming and Architecture) Final Project☆21Updated 9 months ago
- [ECCV 2022] SuperTickets: Drawing Task-Agnostic Lottery Tickets from Supernets via Jointly Architecture Searching and Parameter Pruning☆19Updated 2 years ago
- Summary of system papers/frameworks/codes/tools on training or serving large model☆56Updated 9 months ago
- Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity☆166Updated 11 months ago
- ☆30Updated 3 months ago
- ☆16Updated this week
- AFPQ code implementation☆15Updated 10 months ago
- ☆138Updated 2 months ago
- Patch convolution to avoid large GPU memory usage of Conv2D☆73Updated 3 months ago