【Bug已解决】GroupQueryAttentionFusion produces an invalid graph when a GQA node has more than 9 inputs …
【Bug已解决】GroupQueryAttentionFusion produces an invalid graph when a GQA node has more than 9 inputs (e.g. attention_bias) — "sum of input arg count is not equal to size of input defs" 解决方案
一、现象长什么样
ONNX Runtime 的图优化器里有一个…
2026/8/13 10:07:18