Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Docs
  • Enterprise
  • Pricing

  • Log In
  • Sign Up

EricB
/
kernels-paged-attention-metal

kernel
Model card Files Files and versions
xet
Community
1
kernels-paged-attention-metal / paged-attention-metal
136 kB
  • 2 contributors
History: 17 commits
EricB's picture
EricB HF Staff
Add fp8 support
0cd49c5 6 months ago
  • attention
    Add fp8 support 6 months ago
  • cache
    Add fp8 support 6 months ago
  • cache.mm
    22 kB
    Add fp8 support 6 months ago
  • convert_fp8.metal
    2.96 kB
    Add fp8 support 6 months ago
  • convert_fp8.mm
    5.57 kB
    Add fp8 support 6 months ago
  • device.mm
    639 Bytes
    Run clang-format 6 months ago
  • float8.metal
    3.91 kB
    Add fp8 support 6 months ago
  • paged_attention.mm
    28.1 kB
    Add fp8 support 6 months ago
  • utils.metal
    10.3 kB
    Add utils.metal 6 months ago