Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets new
  • Docs
  • Enterprise
  • Pricing
    • Website
      • Tasks
      • HuggingChat
      • Collections
      • Languages
      • Organizations
    • Community
      • Blog
      • Posts
      • Daily Papers
      • Hardware
      • Learn
      • Discord
      • Forum
      • GitHub
    • Solutions
      • Team & Enterprise
      • Hugging Face PRO
      • Enterprise Support
      • Inference Providers
      • Inference Endpoints
      • Storage Buckets

  • Log In
  • Sign Up

Kernels:
webgpu-kernels
/
com.microsoft.MatMulNBits

Kernel card Files Files and versions
xet
Community
com.microsoft.MatMulNBits / build /webgpu
218 kB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 2 commits
Xenova's picture
Xenova HF Staff
sync c928d21e6cc1
19bef0f verified 6 days ago
  • bench.json
    32.3 kB
    sync 2e7068faf55e 7 days ago
  • manifest.json
    61.2 kB
    sync c928d21e6cc1 6 days ago
  • matmul-nbits-dp4a-quantize.wgsl.jinja
    1.57 kB
    sync 2e7068faf55e 7 days ago
  • matmul-nbits-gemv-q4.wgsl.jinja
    5.28 kB
    sync c928d21e6cc1 6 days ago
  • matmul-nbits-q4-dp4a-prefill.wgsl.jinja
    3.65 kB
    sync 2e7068faf55e 7 days ago
  • matmul-nbits-q4-prefill-tile4x4.wgsl.jinja
    6.13 kB
    sync 2e7068faf55e 7 days ago
  • matmul-nbits-q4-prefill-tiled-reg.wgsl.jinja
    8.08 kB
    sync 2e7068faf55e 7 days ago
  • matmul-nbits-q4-prefill-tiled.wgsl.jinja
    4.99 kB
    sync 2e7068faf55e 7 days ago
  • matmul-nbits-q4-sgmat.wgsl.jinja
    9.31 kB
    sync c928d21e6cc1 6 days ago
  • matmul-nbits.wgsl.jinja
    2.32 kB
    sync 2e7068faf55e 7 days ago
  • metadata.json
    1.4 kB
    sync c928d21e6cc1 6 days ago
  • test.json
    81.5 kB
    sync c928d21e6cc1 6 days ago