-
Running into the following issue:
```
marc@mbp mflux-tests % mflux-generate --prompt "hello" -m dev
Fetching 8 files: 100%|████████████████████████████████████████████████████████████████████████…
-
Hello,
1. Can I know the source files where winograd convolution code is implemented?
2. Also is there scope/plan for accuracy improvement of winograd convolution?
-
One of the issues faced during SDXL support (https://github.com/openxla/iree/pull/16854) was the missing support for operations added in LinalgExt on all codegen backends i.e, CPU, SPIRV and LLVMGPU.
…
-
Is it possible to implement Winograd Convolution with 8 bit weights and activations? The intermediate transformations cause overflows which results in the loss of accuracy of the overall CNN. Is anyon…
-
Please use the [caffe-users list](https://groups.google.com/forum/#!forum/caffe-users) for usage, installation, or modeling questions, or other requests for help.
_Do not post such requests to Issues…
-
My success/failure cases here have been a bit inconsistent, so I'll try to be explicit as possible.
@daveliddell and I are trying to get SDXL VAE on f32 working with AIE offload, and first we need …
-
Each configuration should be controlled separately. Group convolution needs to be double checked. Then 16/16 F(2,3) and F(3,3) to be tested on a network level. I guess those could be enabled for norma…
-
Hi!
I have run the F(2x2, 3x3) you have provided in this repo, and I get the definitely right result using Winograd convolution algorithm.
Then, I want to try F(4x4, 3x3), so I change three tr…
-
Hi,
I used Windows system on Snapdragon ARM CPU and noticed that kernel can't build:
`arm_conv::winograd::weight_transform::a64_fp16_4x4_3x3`
and other fp16 kernels in:
`src/core/NEON/kernels/co…
-
(Lots of red herrings here, see https://github.com/iree-org/iree/issues/17635#issuecomment-2163644331 for latest issue description)
---
Splitting off of https://github.com/llvm/torch-mlir/issu…