Hello! I tuned a CNN model trained by tensorflow, and I test it’s performence, I found the whole TVM infer time is bigger than the tensofrflow far away
Extract tasks…
Cannot find config for target=cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -
thread_warp_size=32, workload=(‘dense_small_batch.cuda’, (‘TENSOR’, (2500, 512), ‘float32’),
(‘TENSOR’, (6600, 512), ‘float32’), None, ‘float32’). A fallback configuration is used, which may bring
great performance regression.
How to fix this non-exists configuration case?