In TensorRT a trt engine can be serialized and deserialized like this:
> with open(“sample.engine”, “wb”) as f:
> f.write(engine.serialize())
> with open(“sample.engine”, “rb”) as f, trt.Runtime(TRT_LOGGER) as
> runtime:
> engine = runtime.deserialize_cuda_engine(f.read())
In TVM a tvm module is alway saved as a shared library like this:
> with relay.build_config(opt_level=3):
> _, resnet18_lib, _ = relay.build_module.build(resnet18_mod, "cuda",
> params=resnet18_params)
> resnet18_lib.export_library("deploy.so")
Is there a way to serialize a tvm module into a string like the serialized
engine in tensorrt?
---
[Visit
Topic](https://discuss.tvm.ai/t/is-there-a-way-to-serialize-a-tvm-module-into-a-string-like-the-serialized-engine-in-tensorrt/7042/1)
to respond.
You are receiving this because you enabled mailing list mode.
To unsubscribe from these emails, [click
here](https://discuss.tvm.ai/email/unsubscribe/cd163b969d3183a3bfa0d74ab18e64d1694b0e20b724bfebe2d93456d809552c).
