Dayuxiaoshui opened a new pull request, #18524: URL: https://github.com/apache/tvm/pull/18524
Fixes #18441 Previously, the TVM frontend incorrectly assumed 4D input dimensions for scaled_dot_product_attention, causing an InternalError when the actual input was 2D (seq_len, head_dim). This fix: - Detects input dimensionality (2D vs 4D) - For 2D inputs: expands to 4D, calls attention, then squeezes back - For 4D inputs: maintains existing behavior - Adds test case for 2D input scenario - Updates verify_model_numerically to use strict=False for export -- 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] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
