Bump NeMo to use a trunk commit instead of a branch for Evo2 fixes and inference.

[cspades]

Description

• Update EVO2 tests according to Hyena arch changes #798 (Fix masked token loss refactor from NeMo bump. #855) depends on a NeMo branch, which has been merged into NeMo main: Migrate Hyena to Megatron inference_context. NVIDIA-NeMo/NeMo#13436. Update to point to this trunk commit.

Details

• NeMo ToT reverted the cp_size argument for masked_token_loss (Fix loss compute and reduction NVIDIA-NeMo/NeMo#13295), so we do the CP reduction on our side now...
  • Future Megatron bump will add the * cp_size multiplier to the loss, and break our inference unit tests due to torch.inference_mode() usage in Megatron.

[jstjohn]

Ship

[codecov-commenter]

Codecov Report

❌ Patch coverage is 92.85714% with 1 line in your changes missing coverage. Please review.
✅ Project coverage is 84.41%. Comparing base (635a8f4) to head (2db0330).
⚠️ Report is 106 commits behind head on main.
✅ All tests successful. No failed tests found.

Files with missing lines	Patch %	Lines
...onemo/geneformer/model/finetune_token_regressor.py	75.00%	1 Missing ⚠️

Additional details and impacted files

@@            Coverage Diff             @@
##             main     #861      +/-   ##
==========================================
+ Coverage   84.38%   84.41%   +0.03%     
==========================================
  Files         138      138              
  Lines        8691     8695       +4     
==========================================
+ Hits         7334     7340       +6     
+ Misses       1357     1355       -2     

Files with missing lines	Coverage Δ
...kages/bionemo-evo2/src/bionemo/evo2/run/predict.py	79.72% <100.00%> (+0.13%)	⬆️
...packages/bionemo-llm/src/bionemo/llm/model/loss.py	59.49% <100.00%> (-0.51%)	⬇️
...ionemo-llm/src/bionemo/llm/utils/megatron_utils.py	100.00% <100.00%> (ø)
...onemo/geneformer/model/finetune_token_regressor.py	60.97% <75.00%> (+0.49%)	⬆️

... and 1 file with indirect coverage changes