reminisce opened a new pull request #4489: Add __float2half_rn for cuda compute capabilities less than 53 URL: https://github.com/apache/incubator-tvm/pull/4489 ### Description When float32 consts are converted to float16, `__float2half_rn`, which is officially defined in `cuda_fp16.h` and included for cuda compute capabilities >= 53, is invoked. In this PR, the same function is added in cuda code gen for cuda compute capabilities < 53. Thank @yzhliu for pointers.
---------------------------------------------------------------- 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. For queries about this service, please contact Infrastructure at: [email protected] With regards, Apache Git Services
