hmz0412 commented on issue #17572: URL: https://github.com/apache/tvm/issues/17572#issuecomment-2561709786
I want to achieve the effect of allocating a buffer that is related to the number of KV tokens in each batch. However, since dynamic allocation is not possible, how can I achieve this while complying with TIR constraints? For example: Is it possible to allocate the buffer enough to each batch outside the main loop and then use it later? Or are there other approaches? -- 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]
