The GitHub Actions job "Lint" on tvm.git/tflite-quantized-avgpool has failed. Run started by GitHub user Theoo1997 (triggered by Theoo1997).
Head commit for run: a2adbb252de5c6725d3a40066be2bce5ea5e752c / Theoo1997 <[email protected]> [Relax][TFLite] Size the quantized AVERAGE_POOL_2D accumulator from the input type The exact-sum lowering pre-scales the input by the window size, so its accumulator must hold max|x| * window^2. The overflow guard assumed 8-bit input (255 * window^2), but the branch also accepts int16: a VALID 17x17 pool of int16 32767 needs 2.7e9 and returned -18657 instead of 32767. Derive the bound from the input dtype's range (128 int8, 255 uint8, 32768 int16) and use int32 when it fits, int64 otherwise; the rounding and the divide run in the same type. int8 lowering is unchanged. Adds test_quantized_avg_pool2d_large_window_does_not_overflow (int16 +-extremes, int8, uint8, 17x17 window). Report URL: https://github.com/apache/tvm/actions/runs/34564827959 With regards, GitHub Actions via GitBox --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
