srkreddy1238 commented on code in PR #13867: URL: https://github.com/apache/tvm/pull/13867#discussion_r1103987954
########## gallery/how_to/deploy_models/deploy_model_on_adreno.py: ########## @@ -115,6 +115,67 @@ # android 1 1 0 # ---------------------------------- +################################################################# +# Configuration +# ------------- + +import os +import torch +import torchvision +import tvm +from tvm import te +from tvm import relay, rpc +from tvm.contrib import utils, ndk +from tvm.contrib import graph_executor +from tvm.relay.op.contrib import clml +from tvm import autotvm + +# Adreno devices are efficient with float16 compared to float32 Review Comment: I definitely agree on this from readability point of view. But for someone to modify the settings and tryout may be a bit difficult. Let me follow the old way with a documentation on top about these settings. -- 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]
