aredden / torch-cublas-hgemm

Related projects ⓘ

Alternatives and complementary repositories for torch-cublas-hgemm

• srush / triton-autodiff
  Experiment of using Tangent to autodiff triton
  ☆72Updated 9 months ago
• cloneofsimo / min-fsdp
  ☆73Updated 4 months ago
• neuralmagic / compressed-tensors
  A safetensors extension to efficiently store sparse quantized tensors on disk
  ☆50Updated this week
• mgmalek / efficient_cross_entropy
  ☆77Updated 5 months ago
• ethansmith2000 / TransformerExperiments
  ☆18Updated last month
• chu-tianxiang / QuIP-for-all
  QuIP quantization
  ☆46Updated 8 months ago
• GindaChen / FlexFlashAttention3
  FlexAttention w/ FlashAttention3 Support
  ☆27Updated last month
• mobiusml / gemlite
  Simple and fast low-bit matmul kernels in CUDA / Triton
  ☆145Updated this week
• timudk / flux_triton
  Writing FLUX in Triton
  ☆30Updated last month
• sekstini / basedxl
  ☆15Updated 8 months ago
• tridao / flash-attention-wheels
  ☆44Updated 11 months ago
• lianakoleva / no-libtorch-compile
  ☆17Updated 3 weeks ago
• cloneofsimo / efae
  ☆21Updated 5 months ago
• BlinkDL / LinearAttentionArena
  Here we will test various linear attention designs.
  ☆56Updated 6 months ago
• ai-compiler-study / triton-kernels
  Triton kernels for Flux
  ☆17Updated last week
• 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.
  ☆35Updated 4 months ago
• amirzandieh / HyperAttention
  Triton Implementation of HyperAttention Algorithm
  ☆46Updated 11 months ago
• aredden / torch-bnb-fp4
  Faster Pytorch bitsandbytes 4bit fp4 nn.Linear ops
  ☆23Updated 8 months ago
• cloneofsimo / min-max-gpt
  Minimal (400 LOC) implementation Maximum (multi-node, FSDP) GPT training
  ☆113Updated 7 months ago
• nshepperd / flash_attn_jax
  JAX bindings for Flash Attention v2
  ☆79Updated 4 months ago
• yifuwang / symm-mem-recipes
  ☆12Updated last month
• chengzeyi / ParaAttention
  [WIP] Context parallel attention that works with torch.compile
  ☆49Updated this week
• euclaise / supertrainer2000
  ☆49Updated 8 months ago
• INT-FlashAttention2024 / INT-FlashAttention
  ☆47Updated 2 months ago
• cchan / tccl
  extensible collectives library in triton
  ☆72Updated last month
• mit-han-lab / patch_conv
  Patch convolution to avoid large GPU memory usage of Conv2D
  ☆79Updated 5 months ago
• Zyphra / tree_attention
  Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clusters
  ☆104Updated last month
• apple / ml-ademamix
  ☆48Updated last week
• evanatyourservice / kron_torch
  An implementation of PSGD Kron second-order optimizer for PyTorch
  ☆16Updated this week
• dvruette / barrel-rec-pytorch
  ☆53Updated 10 months ago