rickzx opened a new pull request, #16606: URL: https://github.com/apache/tvm/pull/16606
In GPT-2, attention calculation requires an additional feature `scale_attn_by_inverse_layer_idx`. It provides a scaling factor per attention layer when calculating the attention score, before applying the softmax function. This PR supports this additional parameter in KV cache. -- 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]
