gau-nernst / quantized-training
Explore training for quantized models
☆17Updated 3 months ago
Alternatives and similar repositories for quantized-training:
Users that are interested in quantized-training are comparing it to the libraries listed below
- An experimental CPU backend for Triton (https//github.com/openai/triton)☆40Updated last month
- extensible collectives library in triton☆85Updated 3 weeks ago
- ☆78Updated 5 months ago
- A bunch of kernels that might make stuff slower 😉☆34Updated this week
- High-speed GEMV kernels, at most 2.7x speedup compared to pytorch baseline.☆106Updated 9 months ago
- TileFusion is an experimental C++ macro kernel template library that elevates the abstraction level in CUDA C for tile processing.☆82Updated this week
- Fast low-bit matmul kernels in Triton☆291Updated this week
- Boosting 4-bit inference kernels with 2:4 Sparsity☆72Updated 7 months ago
- ☆68Updated 3 weeks ago
- Tritonbench is a collection of PyTorch custom operators with example inputs to measure their performance.☆111Updated last week
- ☆31Updated last week
- Ahead of Time (AOT) Triton Math Library☆57Updated last week
- ☆21Updated last month
- Fast Hadamard transform in CUDA, with a PyTorch interface☆174Updated 11 months ago
- ☆68Updated 3 months ago
- Standalone Flash Attention v2 kernel without libtorch dependency☆108Updated 7 months ago
- Collection of kernels written in Triton language☆120Updated 2 weeks ago
- PyTorch bindings for CUTLASS grouped GEMM.☆81Updated 5 months ago
- ☆27Updated 3 months ago
- Applied AI experiments and examples for PyTorch☆262Updated last month
- High-Performance SGEMM on CUDA devices☆90Updated 3 months ago
- llama INT4 cuda inference with AWQ☆54Updated 3 months ago
- Framework to reduce autotune overhead to zero for well known deployments.☆65Updated last week
- This repository contains the experimental PyTorch native float8 training UX☆223Updated 8 months ago
- ShiftAddLLM: Accelerating Pretrained LLMs via Post-Training Multiplication-Less Reparameterization☆106Updated 6 months ago
- ☆157Updated last year
- ☆55Updated 2 weeks ago
- ☆103Updated 7 months ago
- Benchmark code for the "Online normalizer calculation for softmax" paper☆91Updated 6 years ago
- Cataloging released Triton kernels.☆217Updated 3 months ago