onnxruntime
Update qMoE spec to support block quantization
#25641
Merged

Commits
  • update qMoE to support block_size
    tianleiwu committed 353 days ago
  • fix ,
    tianleiwu committed 353 days ago
  • format
    tianleiwu committed 353 days ago
  • update doc
    tianleiwu committed 353 days ago
Loading