Skip to content

fix(quantization): skip MaxPool during FP8 static quantization - #28488

Merged
tianleiwu merged 3 commits into
microsoft:mainfrom
Rishi-Dave:rishidave/fix/fp8-static-quant-maxpool
Jun 3, 2026
Merged

fix(quantization): skip MaxPool during FP8 static quantization#28488
tianleiwu merged 3 commits into
microsoft:mainfrom
Rishi-Dave:rishidave/fix/fp8-static-quant-maxpool

refactor(quantization): reuse FLOAT8_TYPES in matmul and cover QMaxPo…

e8e27ef
Select commit
Loading
Failed to load commit list.
GitHub Advanced Security / CodeQL succeeded Jun 3, 2026 in 2s

No new alerts in code changed by this pull request

View all branch alerts.

Annotations

Check warning on line 21 in onnxruntime/python/tools/quantization/operators/maxpool.py

See this annotation in the file changed.

Code scanning / CodeQL

Use of the return value of a procedure Warning

The result of
QuantOperatorBase.quantize
Loading
is used even though it is always None.