@FIR-790 -LLama.cpp: Add all Src tensor shape & size

[akapoor3518]

Here are output look like after printing src tensor size/shape

=== GGML Detailed Op Perf (36059.700 ms total) ===
Backend Op Runs Total ms Avg ms ne[0] ne[1] ne[2] ne[3]
CPU GET_ROWS 4 9.937 2.484 2048 7 1 1
src0 : ne[0]= 2048 ne[1]= 32003 ne[2]= 1 ne[3]= 1
src1 : ne[0]= 7 ne[1]= 1 ne[2]= 1 ne[3]= 1
CPU RMS_NORM 4 0.162 0.041 2048 7 1 1
src0 : ne[0]= 2048 ne[1]= 7 ne[2]= 1 ne[3]= 1
TSAVORITE MUL 1 150.026 150.026 2048 7 1 1
src0 : ne[0]= 2048 ne[1]= 7 ne[2]= 1 ne[3]= 1
src1 : ne[0]= 2048 ne[1]= 1 ne[2]= 1 ne[3]= 1
CPU MUL_MAT 4 31.865 7.966 2048 7 1 1
src0 : ne[0]= 2048 ne[1]= 2048 ne[2]= 1 ne[3]= 1
src1 : ne[0]= 2048 ne[1]= 7 ne[2]= 1 ne[3]= 1
CPU RESHAPE 4 0.032 0.008 64 32 7 1
src0 : ne[0]= 2048 ne[1]= 7 ne[2]= 1 ne[3]= 1
CPU ROPE 4 0.282 0.070 64 32 7 1
src0 : ne[0]= 64 ne[1]= 32 ne[2]= 7 ne[3]= 1
src1 : ne[0]= 7 ne[1]= 1 ne[2]= 1 ne[3]= 1
CPU MUL_MAT 4 4.767 1.192 256 7 1 1
src0 : ne[0]= 2048 ne[1]= 256 ne[2]= 1 ne[3]= 1
src1 : ne[0]= 2048 ne[1]= 7 ne[2]= 1 ne[3]= 1
CPU RESHAPE 3 0.002 0.001 64 4 7 1
src0 : ne[0]= 256 ne[1]= 7 ne[2]= 1 ne[3]= 1
CPU ROPE 4 0.044 0.011 64 4 7 1
src0 : ne[0]= 64 ne[1]= 4 ne[2]= 7 ne[3]= 1
src1 : ne[0]= 7 ne[1]= 1 ne[2]= 1 ne[3]= 1
CPU MUL_MAT 3 3.539 1.180 256 7 1 1