QNNPACK
QNNPACK copied to clipboard
pytorch
Quantized Neural Network PACKage - mobile-optimized implementation of quantized neural network operators
I am using Unet model for semantic segmentation. I pass a batch of images to the model. The model is expected to output 0 or 1 for each pixel of...
Hi - is there a plan to support nn.ConvTranspose2d for both QNNPACK and FBGEMM? I am using this in my model. After applying QNNPACK quantization techniques (both post training static...
Hi, @hlu1 I am wondering what actually XZP ukernel is and how it works in convolution. Thanks
Hey there, Is QNNPACK still being actively developed? I noticed that the last activity was in August of last year but it does seem like an important part of Pytorch....
I'm trying to add a package for QNNPACK to the [Spack package manager](https://spack.io). I see that QNNPACK downloads its own dependencies, and that this can be avoided by setting `*_SOURCE_DIR`...
I found 8x8__aarch32_neonfp16arith is this the fp16 gemm method?
Micro-kernels implementation of the following: * Q8GEMM with per-channel weights quantization parameters (.c) + unit tests + benchmarks * Q8GEMM with per-channel weights quantization parameters for AARCH32 (.S) + unit...
This is a preliminary version in order to get some feedback. The goal is adding support in GEMM with different kernel quantization parameters per output channel. Changes: * Modified version...
I am opening this issue to see if anyone is interested in contributing. As QNNPACK have minimum dependecy, it is possible to use amalgamation and emscripten to build a javascript...
