finn
finn copied to clipboard
Xilinx
Dataflow compiler for QNN inference on FPGAs
More of a personal preference, but I assume I am not alone. I like to specify my model or "experiment" configurations as well as the metrics collected in YAML format...
When running some automated finn builds by some experiment manager doing parameter sweeps, the jobs failed with some TTY issues from within docker, which I have tracked down to the...
Hi @auphelia @williamliao28, I am facing this issue where Concat layer is not getting converted to HLS layer. I tried the transformation InferConCatLayer(), but still it dint infer streaming Concat...
Introduces a step that splits a dataflow graph into multiple nodes based on the device ID and adds some builder logic to make multi FPGA builds work. The idea is...
~~This PR should be merged after https://github.com/Xilinx/finn/pull/930.~~ This PR is now the first one that should be merged. This PR allows circumventing the limited address space offered by Coyote for...
This PR adds support for generating a bitstream containing the FINN kernel inside a Coyote shell. For now, it only takes care of the HW design side. This PR is...
### Discussed in https://github.com/Xilinx/finn/discussions/937 Originally posted by **pkdeep** December 10, 2023 Hello I am trying to run BBN-PYNQ example notebook with TFC (for MNIST data) network with weight = 2bits...
### Discussed in https://github.com/Xilinx/finn/discussions/932 Originally posted by **Madhurima8** December 3, 2023 I am facing an issue while installing FINN with docker. when I ran this command to verify the installation...
## Quick summary This is not really a bug report, it is more a collection of missing support and minor annoyances I am encountering while working towards streamlining and eventually...
## Details As discussed in #883, grouped convolutions (i.e., `groups>1`) are only supported when `in_channels == out_channels == groups`. `LowerConvsToMatMul` fails with a reshape error. ### New behavior Ideally, it...
