Chris Siefert

Tpetra: Fixing Doxygen for FECrsMatrix

12

Issue: #13189 Tests: n/a Stakholder feedback: @avfav1235

MueLu: Fixing Maxwell1 so it robustly works w/ repartitioning

14

Issue: #11214 Stakeholder feedback: MOI test passes. Tests: Added new input deck to Maxwell test which would have died before.

As reported by our friends from dealII: Epetra has these, Tpetra does not. We should fix this.

Tpetra: Reduce Compilation of ordinal-as-scalar objects

10

In order to provide an analogue for Epetra_IntVector, Tpetra rebuilds sizable portions of its library with Scalar=GO and Scalar=int (if int is not the GO). We clearly need Vector for...

Language modeling examples do not show how to do multi-gpu training / fine-tuning

10

### System Info - `transformers` version: 4.41.2 - Platform: Linux-5.15.0-1042-nvidia-x86_64-with-glibc2.35 - Python version: 3.9.18 - Huggingface_hub version: 0.23.3 - Safetensors version: 0.4.2 - Accelerate version: 0.31.0 - Accelerate config: not...

Github action gateway timeout

1

### What was wrong? I'm using coveralls through a github action. There are probably about ~50k gcov files that our testing generates. We get finish the file processing and then...

Any idea what that means? I'm using a fine-grained token with admin permissions

Tpetra/Ifpack2: Better handling of non-GPU aware MPI

6

Largely from discussions with @vbrunini and @jjellio , we should have a unified way of supporting the equivalent TPETRA_ASSUME_GPU_AWARE_MPI across the solver stack (Ifpack2's TriDi solver ignores this). Moreover, if...

Trilinos: Remove use of Kokkos Deprecated Code

4

Specifically, HIP* moved out of Kokkos::Experimental into plain ol' Kokkos @lucbv

MueLu: Provide version of ML's SetDefaults that doesn't require ML

3

As requested by @micpowe's project.