DeepSpeed
Selective dequantization
#5375
Merged
Overview
Commits
11
Changes
View On GitHub
Commits
  • Optimize the fp-dequantizer to get high memory-BW utilization
    sfc-gh-reyazda committed 2 years ago
  • Add selective-deqamtoze function for dequantizing the tensor partially
    sfc-gh-reyazda committed 2 years ago
  • Merge branch 'master' into selective-dequantization
    loadams committed 2 years ago
  • Merge branch 'master' into selective-dequantization
    RezaYazdaniAminabadi committed 2 years ago
  • Merge branch 'master' into selective-dequantization
    loadams committed 2 years ago
  • Merge branch 'master' into selective-dequantization
    RezaYazdaniAminabadi committed 2 years ago
  • fix formatting
    sfc-gh-reyazda committed 2 years ago
  • Merge branch 'microsoft:master' into selective-dequantization
    RezaYazdaniAminabadi committed 2 years ago
  • Merge branch 'master' into selective-dequantization
    RezaYazdaniAminabadi committed 2 years ago
  • Merge branch 'master' into selective-dequantization
    RezaYazdaniAminabadi committed 2 years ago
  • Merge branch 'master' into selective-dequantization
    loadams committed 2 years ago
FAQ Terms Privacy Refunds Impressum
Loading