hyongtao opened a new pull request #8311: URL: https://github.com/apache/tvm/pull/8311
Author: Yongtao Huang <[email protected]> Date: Wed Jun 23 19:44:08 2021 +0800 The dockerfiles are apply to deploy and test TVM environments (including CPU and NVIDIA_GPU) easily. Long log: - There are some errors when we re-build official dockerfile like demo_cpu: https://discuss.tvm.apache.org/t/error-about-tvm-docker/10301 - I have build CPU_TVM and NVIDIA_GPU_TVM docker, which includes inference envs and code. - This can help us verify and deploy our ML model directly. Signed-off-by: Yongtao Huang <[email protected]> -- 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]
