masahi opened a new pull request, #15951: URL: https://github.com/apache/tvm/pull/15951
This is necessary for Mistral support. A new attribute `window_size` has been added to `nn.attention(...)` op, and such sliding-window attention runs efficiently via flash attention. I updated our flash attention submodule to pick up the support for sliding window in https://github.com/tlc-pack/libflash_attn/pull/4. @sunggg @yelite @cyx-6 @vinx13 -- 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]
