Do someone knows where are the codes that specify the order of the cuda kernel
arguments list or map the build args to the cuda kernel arguments?
---
[Visit
Topic](https://discuss.tvm.apache.org/t/whatt-the-arguments-order-of-tvm-generated-cuda-kernel/8422/2)
to respond.
You are receivin
The arguments list of The tvm.build and Function is the same, however, it is
not the same with the generated cuda kernel. For the cuda kernel, I found some
times the outputs arguments is before the inputs, while some times it's not.
Can I get the order or mapping of the cuda kernel arguments ?
from tvm import relay
from tvm.relay import testing
import numpy as np
from infrastructure import get_ref_result
batch_size = 1
num_class = 1000
image_shape = (3, 224, 224)
data_shape = (batch_size,) + image_shape
out_shape = (batch_size, num_class)
dtype="float32"
mod, params = relay.testing.m
have you tried some pre-trained model instead of a model created from scratch
using relay which has dynamic shape input, how is that performance using vm
runtime?
---
[Visit
Topic](https://discuss.tvm.apache.org/t/vm-the-performance-degradation-of-vm-runtime-and-dynamic-shape-support-comp
I am going through the VTA tutorial for matrix multiplication given in
https://tvm.apache.org/docs/vta/tutorials/matrix_multiply.html
A_2 is the input vector tensor and B_2 is the weight tensor.
As we can see in the lowered code below, the last parameter's value (which
corresponds to memory st
To test without a config, remove the `autotvm.apply_history_best` with
statement.
`params` is a dictionary mapping from the name of a weight to the actual values
of the weight. In this case, you have no weights, so it is just the empty
dictionary.
---
[Visit
Topic](https://discuss.tvm.a
Hi, just learned about TVM and seems like a very interesting project.
Does it have similar design goals to ONNX ? i.e: Portability and efficient
inference on different target hardwares ?
Would be glad to understand if they are located on different layers in the
Inference stack, and how their p
