powderluv
powderluv
For large graphs it would be nice to have the ability to define custom subgraphs along with nodes in them and name them in the Shape Drawer. This allows for...
Can we please have a feature to select a few nodes and add them to a subgraph ?
TODO: Do we depend on XNNPACK's cpuinfo or do we get the version with RUY. Needs some mods to RUY cmake.
Great work. How do I generate an "official" image ? I would like some customizations before deploying. Are there any scripts you use to build the release image ? Couldn't...
So update to 2.8.12.2 (in Ubuntu 14.04) CentOS 7 has a way to install CMake3. This avoids the warning in newer CMakes: flatcc/CMakeLists.txt:5 (cmake_minimum_required): Compatibility with CMake < 2.8.12 will...
[SHARK](https://github.com/nod-ai/SHARK) is a high performance codegen compiler and runtime built on MLIR, IREE and custom RL based tuning infrastructure. [Here](https://nod.ai/shark-the-fastest-runtime/) are some results of using SHARK for the same model...
How do you see distributed execution support in taskflow ? Would it ride on something like hpx ? Or will you natively support such an executor in the future. Any...
First thank you for this awesome work. I was going to start from diff'ing the 0.8 source but then found your repo. I was going to try to port from...
https://aur.archlinux.org/packages/hostapd-rtl871xdrv/ Compiles and tests on 2.9 with 8814au and 8822BU cards. However the need for this driver is questionable since the default one supports the same features. But maybe there...
### What happened? Splitting out the CPU issue reported earlier in https://github.com/google/iree/issues/9536 SAVE_TEMPS is at : gs://iree-shared-files/nod-perf/anush/iree_save_temps_albert_cuda/ ``` E assert True == False E + where False = compare_tensors_tf(, array([[[...