I am trying to call cblas libraries when "cblas" is specified in the target
libs and the target is x86. This needs to happen in two places: dense and
batch_matmul.
Dense is straightforward because x86 already has an overridden compute and
schedule. However, batch_matmul only has an overridden
ONNX models get converted to Relay IR, which gets codegenned using Topi
operator implementations, which support CUDA.
Yes, a model coming in from ONNX should support CUDA. What error are you seeing?
---
[Visit Topic](https://discuss.tvm.ai/t/regarding-onnx-cuda-support/3723/2) to
respond
I would like to share the solution to my problem described in the previous
comment.
The issue is that I defined the set of outputs of the model as a set using as
follows:
```
outputs = {'output1', 'output2', 'output3'}
mod, params = relay.frontend.from_tensorflow(graph_def, layout=layout,
ou
Hi @vinx13
Could you confirm please if only the NCHW layout can be quantized and not NHWC?
Thanks
---
[Visit
Topic](https://discuss.tvm.ai/t/quantization-autotvm-performance-degradation-due-to-transpose-ops-when-nchw-layout-is-used/3561/8)
to respond.
You are receiving this because you
Is operator fusing supported when using AutoTVM with GPU?
1. From the [paper](https://arxiv.org/pdf/1802.04799.pdf) it seems that
operator fusion is happening before AutoTVM (operator fusion is described in
section 3, while AutoTVM in section 5).
2. There is [answer](https://discuss.tvm.ai/t/
Hi,
I am testing a model with 3 outputs, however, when I use `m.get_output(0, ) `
for example for index 0, I always get different outputs. This means that the
outputs are randomly mapped to the output indexes.
Is this a bug? or is there any way to get the output indexes in a deterministic
I see. Thanks a lot for your explanations.
---
[Visit Topic](https://discuss.tvm.ai/t/chisel-implementations/3707/5) 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/513ee086b
