Request for Ampere GPU Support in FlashMLA​

[ehartford]

I would like to request support for NVIDIA Ampere architecture GPUs in FlashMLA. I understand that many of the current optimizations are specific to Hopper GPUs, but having a "lite" version compatible with Ampere would be highly beneficial.​

Extending compatibility to Ampere GPUs would allow a broader range of users to utilize FlashMLA, especially those without access to Hopper GPUs.​

[radna0]

+1

[ubergarm]

See #66