Update GEMM (#424)

* Organize and collect metal subroutine templates and elements in `metal/kernels/steel/`
* Update gemm elements for better performance 
* Add split-K specialization for gemm
* Add `addmm` primitive, op and bindings for fused matmul and bias addition 
* Update tests and benchmarks as needed

benchmarks/python/blas/bench_gemm.py

@@ -166,13 +166,13 @@ if __name__ == "__main__":
     dtypes = ("float32", "float16")
     transposes = ("nn", "nt", "tn")
     shapes = (
+        (16, 234, 768, 3072),
+        (1, 64, 64, 25344),
         (16, 1024, 1024, 1024),
         (1, 1024, 1024, 2048),
         (4, 1024, 1024, 4096),
         (4, 1024, 4096, 1024),
         (1, 4096, 4096, 4096),
-        (15, 1023, 1023, 1023),
-        (17, 1025, 1025, 1025),
     )
 
     for dtype in dtypes: