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

  • Log In
  • Sign Up

yongwww
/
trtllm_fp8_block_scale_moe_inputs

Model card Files Files and versions
xet
Community
trtllm_fp8_block_scale_moe_inputs
76.5 GB
  • 2 contributors
History: 3 commits

This model has 2 files scanned as unsafe.

Yong Wu
Add new fused moe workloads for bs=1,16,64
c72f96b 2 months ago
  • bs1
    inputs from SGL serving 3 months ago
  • bs16
    inputs from SGL serving 3 months ago
  • fused_moe_wl
    Add new fused moe workloads for bs=1,16,64 2 months ago
  • .gitattributes
    1.52 kB
    initial commit 3 months ago