how to dump this graph?
---
[Visit
Topic](https://discuss.tvm.apache.org/t/how-to-extract-tvm-module/2167/22) to
respond.
You are receiving this because you enabled mailing list mode.
To unsubscribe from these emails, [click
here](https://discuss.tvm.apache.org/email/unsubscribe/bb6d1de
what's specific meaning search space in TVM
and How to express search space mathematically.
---
[Visit
Topic](https://discuss.tvm.apache.org/t/whats-specific-meaning-search-space-in-tvm/11805/1)
to respond.
You are receiving this because you enabled mailing list mode.
To unsubscribe from
There are a couple of different targets that output something so similar to C
(e.g. CUDA, OpenCL) that some some of the functionality was extracted into a
common superclass, `CodeGenC`. When you specify `target="c"`, it uses
`CodeGenCHost` in `codegen_c_host.cc`. You might look at that for mor
I run my model on rk3399's cpu, it has 4 a53 core and 2 a72 core. when running
the model ,I found only the big cores are occupied. My question is how to make
the rest four little cores to run at the same time to speed the performace.
(before autotvm, my model costs about 500ms, it is too slow)
Hello,
I compiled my relay graph to a DSO library, json graph and a parameter binary
file like below:
graph, lib, lowered_params = relay.build(mod, target="opencl",
target_host="llvm --runtime=c++, params=params)
lib.export_library(os.path.join(build_dir, name+".so"))
When I'm deploying this
from pytorch_pretrained_bert import BertForMaskedLM
import torch
def main(args):
bert_model_origin =
BertForMaskedLM.from_pretrained("bert-large-uncased")
example_tensor = torch.randint(0, 100, (1, 256))
model_int8 = torch.quantization.quantize_dynamic(bert_m
