Alternatives and similar repositories for superblock

Users that are interested in superblock are comparing it to the libraries listed below

• meta-pytorch / float8_experimental
  This repository contains the experimental PyTorch native float8 training UX
  ☆227Updated last year
• jundaf2 / INT8-Flash-Attention-FMHA-Quantization
  ☆160Updated 2 years ago
• cchan / tccl
  extensible collectives library in triton
  ☆91Updated 9 months ago
• srush / triton-autodiff
  Experiment of using Tangent to autodiff triton
  ☆81Updated last year
• facebookresearch / MODel_opt
  Memory Optimizations for Deep Learning (ICML 2023)
  ☆114Updated last year
• facebookresearch / any4
  Quantize transformers to any learned arbitrary 4-bit numeric format
  ☆50Updated 5 months ago
• INT-FlashAttention2024 / INT-FlashAttention
  ☆84Updated 11 months ago
• stanford-futuredata / stk
  ☆115Updated last year
• graphcore-research / out-of-the-box-fp8-training
  Demo of the unit_scaling library, showing how a model can be easily adapted to train in FP8.
  ☆46Updated last year
• tgale96 / grouped_gemm
  PyTorch bindings for CUTLASS grouped GEMM.
  ☆135Updated 7 months ago
• nil0x9 / flash-muon
  Flash-Muon: An Efficient Implementation of Muon Optimizer
  ☆225Updated 6 months ago
• IST-DASLab / Sparse-Marlin
  Boosting 4-bit inference kernels with 2:4 Sparsity
  ☆90Updated last year
• GindaChen / FlexFlashAttention3
  FlexAttention w/ FlashAttention3 Support
  ☆27Updated last year
• graphcore-research / unit-scaling
  A library for unit scaling in PyTorch
  ☆133Updated 5 months ago
• microsoft / AttentionEngine
  ☆116Updated 7 months ago
• gpu-mode / ring-attention
  ring-attention experiments
  ☆161Updated last year
• mit-han-lab / patch_conv
  Patch convolution to avoid large GPU memory usage of Conv2D
  ☆93Updated 11 months ago
• gau-nernst / quantized-training
  Explore training for quantized models
  ☆25Updated 5 months ago
• mgmalek / efficient_cross_entropy
  ☆124Updated last year
• aredden / torch-bnb-fp4
  Faster Pytorch bitsandbytes 4bit fp4 nn.Linear ops
  ☆30Updated last year
• amazon-science / mxfp4-llm
  Official implementation for Training LLMs with MXFP4
  ☆116Updated 8 months ago
• meta-pytorch / tritonbench
  Tritonbench is a collection of PyTorch custom operators with example inputs to measure their performance.
  ☆308Updated last week
• dropbox / gemlite
  Fast low-bit matmul kernels in Triton
  ☆416Updated 2 weeks ago
• NVIDIA / jaxpp
  JaxPP is a library for JAX that enables flexible MPMD pipeline parallelism for large-scale LLM training
  ☆61Updated 2 weeks ago
• tridao / flash-attention-wheels
  ☆59Updated 2 years ago
• thu-ml / Jetfire-INT8Training
  ☆60Updated last year
• SqueezeBits / QUICK
  QUICK: Quantization-aware Interleaving and Conflict-free Kernel for efficient LLM inference
  ☆118Updated last year
• lightmatter-ai / INT-FP-QSim
  Flexible simulator for mixed precision and format simulation of LLMs and vision transformers.
  ☆51Updated 2 years ago
• IBM / triton-dejavu
  Framework to reduce autotune overhead to zero for well known deployments.
  ☆92Updated 3 months ago
• IST-DASLab / Quartet
  ☆114Updated this week