[FEATURE SUPPORT] add gemm python kernel

[LoserCheems]

Summary

• Introduces a reusable matrix multiply-and-accumulate routine for the GEMM operation, impacting the Python implementation and documentation.

Root Cause

• The need for a unified and efficient implementation of the GEMM operation in Python.

Changes

• Added the GEMM helper function in Python and corresponding documentation, including a README update.

Reproduction

• Not applicable as this is an addition rather than a bug fix.

Tests

• Validated the new GEMM implementation through existing test suites.

Compatibility

• No migration concerns or backwards compatibility issues.

Checklist

• Linked issue provided [FEATURE REQUEST] gemm Python kernel implementation #30
• Adds or updates tests
• Updates docs if needed
• No perf regressions