Nick Korovaiko

@miladm I believe it will be Option 2. We typically won't go through the LTC layer when tracing and generating IR nodes. XLA directly takes over and we end up...

This means the metadata.sizes() for `input` was wrong. The metadata sizes() should be coming from `sym_sizes()` . It looks like we didn't refresh the sizes_ field in XLA somewhere. Could...

@wconstab do you happen to know by any chance why jit mode for MOCO was disabled?

I will be editing this list as I come up with more checks: [ ] Make sure that device and jit are routed to model's c-tors so a model actually...

@vanbasten23 @miladm I'm not quite seeing what you guys both are seeing in https://github.com/pytorch/xla/pull/4073 the test included in the PR prints : ``` __str__ BEGIN __str__ END XLASymIntNodeImpl after printing...

@vanbasten23 @miladm Added an example of printing a static value of a `DimensionNode` here: https://github.com/pytorch/xla/pull/4073/commits/1ff4bae6b9fb32ecbf4f72a05dd4e513f0a68e60 This is the output: ``` (pytorch) root@9471890a681a:/home/pytorch/xla/test# python test_str.py __str__ BEGIN __str__ END IR=SizeNode, static=6...

> , then built it via python setup.py install under pytorch/, then went back to HOME, run the above python command. Wouldn't it pick up my local change? This workflow...

could you please paste the command and/or test you are running? @miladm

Interesting! We actually failed on a different unimplemented function than I expected. ``` Thread 1 "python" hit Catchpoint 1 (exception thrown), __cxxabiv1::__cxa_throw (obj=0x55555b7b8160, tinfo=0x7fff4e324728 , dest=0x7fffd54e0ba0 ) at /opt/conda/conda-bld/gcc-compiler_1654084175708/work/build/gcc-final/x86_64-conda-linux-gnu/libstdc++-v3/libsupc++/eh_throw.cc:77 77...

@tucan9389 yes, I'm so terribly sorry for missing yr reply! We are on ``` keras=3.0.1 tensorflow=2.12.0 ``` and python=3.10