"...lm-evaluation-harness.git" did not exist on "dbbc613fd8840f8aa9b780505c29cdcc8a68a1f9"
  • shivadbhavsar's avatar
    Support per-axis quantization (#2390) · 0039b11a
    shivadbhavsar authored
    Reworked the simplify_qdq pass to support:
    
    Per-axis quantization (ie. allow 1D scales and zero points)
    Allow broadcast and transpose ops between dq and quant_op
    0039b11a
simplify_qdq.cpp 9.27 KB