DzAvril opened a new pull request #10597: URL: https://github.com/apache/tvm/pull/10597
I tried to build a vectornet model using Tensorrt with BYOC. I found if TVM_TENSORRT_CACHE_DIR is set, there will be a segmentation fault when loading the Tensorrt engine from cache. This occured during GetBatchSize() in function GetCachedEnginesFromDisk(), and data_entry_ is not initialized correctly. This issue is fixed by put batchsize in engine file instead of getting it by GetBatchSize(). -- 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]
