[TVM Discuss] [Development] NDArray conversion to numpy array take time (around 350ms) with a simple data

No it is not strange, it is expected. `module.run()` is async-ish, to be sure you can insert explicit sync after `run()` --- [Visit Topic](https://discuss.tvm.ai/t/ndarray-conversion-to-numpy-array-take-time-around-350ms-with-a-simple-data/6053/6) to respond. You are receiving this becau

[TVM Discuss] [Development] NDArray conversion to numpy array take time (around 350ms) with a simple data

I think the same but it's quite strange :( --- [Visit Topic](https://discuss.tvm.ai/t/ndarray-conversion-to-numpy-array-take-time-around-350ms-with-a-simple-data/6053/5) to respond. You are receiving this because you enabled mailing list mode. To unsubscribe from these emails, [click he

[TVM Discuss] [Development] [PyTorch] [Frontend] graph input names can change using loaded torchscript

Thanks for clarification. I think this change makes sense to me. --- [Visit Topic](https://discuss.tvm.ai/t/pytorch-frontend-graph-input-names-can-change-using-loaded-torchscript/6055/7) to respond. You are receiving this because you enabled mailing list mode. To unsubscribe from these e

[TVM Discuss] [Development] [PyTorch] [Frontend] graph input names can change using loaded torchscript

PyTorch users should know the correct order of inputs, because PyTorch modules `forward(...)` method expects its inputs to be in the correct order (otherwise they cannot run any training code). [quote="zhiics, post:5, topic:6055"] And it is possible to connect the names after _run_jin_passes?

[TVM Discuss] [Development/RFC] Performing Relay Passes Non-Recursively

Hmm, that's a good point, the other thing I'm currently working on is the [Pattern Language](https://discuss.tvm.ai/t/rfc-relay-program-matching-for-relay-pt-1-a-pattern-language/5833), and I'm noticing some similar kinds of inflexibilities with that. Will think about how to make this a litt

[TVM Discuss] [Development] [PyTorch] [Frontend] graph input names can change using loaded torchscript

The input names are really annoying. I think one use case of the name to shape dict is to avoid the wrong order of the inputs. How hard is it for users to supply the inputs in the correct order? And it is possible to connect the names after _run_jin_passes? --- [Visit Topic](https://disc

[TVM Discuss] [Development/RFC] [RFC][Tensor Core] Optimization of CNNs on Tensor Core

We are pleased to share the codes. Please check the PR: [TOPI][Tensor Core] Conv2d and Dense ops support on Tensor Core #5099. Try to find the code in topi/python/topi/cuda/conv2d_nhwc.py, which is the code that has the same layout as conv2d of Tensor Core. For any questions, please feel fre

[TVM Discuss] [Development] NDArray conversion to numpy array take time (around 350ms) with a simple data

It is likely the inference hasn't been finished when you call `asnumpy()`. That is why `asnumpy` takes some time to complete. --- [Visit Topic](https://discuss.tvm.ai/t/ndarray-conversion-to-numpy-array-take-time-around-350ms-with-a-simple-data/6053/4) to respond. You are receiving this

[TVM Discuss] [Development] [PyTorch] [Frontend] graph input names can change using loaded torchscript

yes, we can repurpose and rename `_check_input_names` to do necessary input validation. For other frontends, I also remember being annoyed for having to supply input names. Unfortunately for them it is too late to fix. We shouldn't repeat the same mistake :wink: --- [Visit Topic](https:

[TVM Discuss] [Development] [PyTorch] [Frontend] graph input names can change using loaded torchscript

That sounds reasonable, maybe we could at least check that the inputs are valid "shape tuples"? Though this is probably a common thing across frontends that could be done. --- [Visit Topic](https://discuss.tvm.ai/t/pytorch-frontend-graph-input-names-can-change-using-loaded-torchscript/605

[TVM Discuss] [Development] [PyTorch] [Frontend] graph input names can change using loaded torchscript

Thanks, it seems to me the best to way to fix this issue is not to require users to supply the correct input names, since this is an impl detail of torch and we can figure out the names in `from_pytorch`. Instead, users should just supply a list of input shapes in correct order. We call `get

[TVM Discuss] [Development] [PyTorch] [Frontend] graph input names can change using loaded torchscript

Hi, I have been testing the PyTorch frontend and have found an issue with using saved torchscript versus in-memory traced torchscript. What I have observed is that the input names to the graph can be altered by the call to `torch._C._jit_pass_inline()`. Which means that the `get_graph_input

[TVM Discuss] [Development] NDArray conversion to numpy array take time (around 350ms) with a simple data

Thank junrushao1994 !! --- [Visit Topic](https://discuss.tvm.ai/t/ndarray-conversion-to-numpy-array-take-time-around-350ms-with-a-simple-data/6053/3) to respond. You are receiving this because you enabled mailing list mode. To unsubscribe from these emails, [click here](https://discuss.

[TVM Discuss] [Development] NDArray conversion to numpy array take time (around 350ms) with a simple data

There is actually one way to do zero-copy from numpy array to DLPack compatible arrays (like tvm ndarray, pytorch tensor, etc) --- [Visit Topic](https://discuss.tvm.ai/t/ndarray-conversion-to-numpy-array-take-time-around-350ms-with-a-simple-data/6053/2) to respond. You are receiving this

Re: [apache/incubator-tvm] [VOTE] VTA HW/SW refactor (#5102)

+1 -- You are receiving this because you are subscribed to this thread. Reply to this email directly or view it on GitHub: https://github.com/apache/incubator-tvm/issues/5102#issuecomment-602421538