AndrewZhaoLuo commented on code in PR #12666:
URL: https://github.com/apache/tvm/pull/12666#discussion_r960212897
##########
python/tvm/relay/transform/fake_quantization_to_integer.py:
##########
@@ -158,23 +157,29 @@ def bias_add(expr, type_map):
"""Rewrite a bias_add op"""
x, b = expr.args
x_t = type_map[x]
- b_t = type_map[b]
- in_scale = fold_constant(x_t.scale)
- in_zero_point = fold_constant(x_t.zero_point)
- if not (
- approx_equal(x_t.scale, b_t.scale)
- and approx_equal(x_t.zero_point, b_t.zero_point)
- and tvm.ir.structural_equal(x_t.dtype, b_t.dtype)
- ):
- b = relay.qnn.op.requantize(
- b,
- b_t.scale,
- b_t.zero_point,
- in_scale,
- in_zero_point,
- out_dtype=x_t.dtype,
- axis=0,
- )
+ if b in type_map:
+ # Ensure bias matches the previous op
+ b_t = type_map[b]
+ in_scale = fold_constant(x_t.scale)
+ in_zero_point = fold_constant(x_t.zero_point)
+ if not (
+ approx_equal(x_t.scale, b_t.scale)
+ and approx_equal(x_t.zero_point, b_t.zero_point)
+ and tvm.ir.structural_equal(x_t.dtype, b_t.dtype)
+ ):
+ b = relay.qnn.op.requantize(
+ b,
+ b_t.scale,
+ b_t.zero_point,
+ in_scale,
+ in_zero_point,
+ out_dtype=x_t.dtype,
+ axis=0,
+ )
+ else:
Review Comment:
Can we just do something like
type_map.get(b, x_t) # assume is x_t's type if b is not fake quantized
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
