[FEATURE SUPPORT] add pytorch geru kernel

[LoserCheems]

Summary

• Introduces a new helper function for the GERU operation in PyTorch, impacting the tensor operations module.

Root Cause

• The implementation of the GERU operation was missing in the PyTorch ops module.

Changes

• Added a tensor update routine that scales and adds the outer product of two vectors.

Reproduction

• Use the geru function with appropriate tensor inputs to observe the updated behavior.

Tests

• No new tests were specified, but existing tests for related operations were verified.

Compatibility

• No migration concerns or backwards compatibility issues identified.

Checklist

• Linked issue provided [FEATURE REQUEST] geru PyTorch kernel implementation #26
• Adds or updates tests
• Updates docs if needed
• No perf regressions