You are viewing a plain text version of this content. The canonical link for it is here.

Posted to discuss-archive@tvm.apache.org by YangShuai via Apache TVM Discuss <no...@discuss.tvm.ai> on 2022/02/16 10:03:32 UTC

[Apache TVM Discuss] [Questions] How to save tvm(tensorrt-runtime) model and load in tensorrt?


I want to save tvm(tensorrt backend) model, and then load use tensorrt c++ api.

So I set env_variable `TVM_TENSORRT_CACHE_DIR`, and model saved as `tvmgen_default_tensorrt_main_0_fp32.meta` and `tvmgen_default_tensorrt_main_0_fp32.plan`, but the size of `tvmgen_default_tensorrt_main_0_fp32.plan` is 3.3K.

It seems that `tvmgen_default_tensorrt_main_0_fp32.plan` only saves model structure. How to save the parameters?





---
[Visit Topic](https://discuss.tvm.apache.org/t/how-to-save-tvm-tensorrt-runtime-model-and-load-in-tensorrt/12100/1) 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/9f3d22e4470f9eb4f37ac5c8ee8e64a4b9c3b27346aaa6d7319d0740418a6b34).