Add initial tuning for M5 pro and max

[jagrit06]

Proposed changes

Adding kernel tunings for larger M5 devices

Checklist

Put an x in the boxes that apply.

• I have read the CONTRIBUTING document
• I have run pre-commit run --all-files to format my code / installed pre-commit prior to committing changes
• I have added tests that prove my fix is effective or that my feature works
• I have updated the necessary documentation (if needed)

[jagrit06]

Here are some brief numbers on M5 max:

  B,     M,     N,     K,   dtype,  t,  tflops_mx
 
  1,  4096,  4096,  4096, float16, nn,     58.196
 
  1,  4096, 14336,  4096, float16, nn,     59.639
 
  1,  4096,  4096, 14336, float16, nn,     54.875
 
  1,  4096,  4096,  4096, float16, nt,     58.375
 
  1,  4096, 14336,  4096, float16, nt,     58.147
 
  1,  4096,  4096, 14336, float16, nt,     52.706

Split-K mammals need separate work and will benefit from splitting at smaller Ks
Will update those in a follow up PR