marsupialtail / sparsednn
Fast sparse deep learning on CPUs
☆51Updated 2 years ago
Related projects ⓘ
Alternatives and complementary repositories for sparsednn
- Research and development for optimizing transformers☆125Updated 3 years ago
- ☆156Updated 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
- Benchmark code for the "Online normalizer calculation for softmax" paper☆59Updated 6 years ago
- ☆167Updated 4 months ago
- ☆45Updated 2 weeks ago
- SparseTIR: Sparse Tensor Compiler for Deep Learning☆131Updated last year
- ☆88Updated 2 months ago
- Training neural networks in TensorFlow 2.0 with 5x less memory☆129Updated 2 years ago
- Applied AI experiments and examples for PyTorch☆166Updated 3 weeks ago
- ☆48Updated this week
- ☆55Updated 5 months ago
- ☆48Updated 8 months ago
- FTPipe and related pipeline model parallelism research.☆41Updated last year
- This repository contains integer operators on GPUs for PyTorch.☆183Updated last year
- llama INT4 cuda inference with AWQ☆48Updated 4 months ago
- ☆131Updated 3 months ago
- A library of GPU kernels for sparse matrix operations.☆249Updated 3 years ago
- PyTorch extension for emulating FP8 data formats on standard FP32 Xeon/GPU hardware.☆100Updated 11 months ago
- System for automated integration of deep learning backends.☆48Updated 2 years ago
- Customized matrix multiplication kernels☆53Updated 2 years ago
- Memory Optimizations for Deep Learning (ICML 2023)☆60Updated 8 months ago
- CUDA templates for tile-sparse matrix multiplication based on CUTLASS.☆49Updated 6 years ago
- extensible collectives library in triton☆71Updated last month
- Several optimization methods of half-precision general matrix vector multiplication (HGEMV) using CUDA core.☆49Updated 2 months ago
- A schedule language for large model training☆141Updated 5 months ago
- A standalone GEMM kernel for fp16 activation and quantized weight, extracted from FasterTransformer☆85Updated 8 months ago
- An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).☆208Updated 3 weeks ago
- Standalone Flash Attention v2 kernel without libtorch dependency☆98Updated 2 months ago