m3 ultra flops estimates based on some quick profiling

Author: AlexCheema

exo/topology/device_capabilities.py

@@ -56,6 +56,7 @@ def to_dict(self):
   "Apple M3": DeviceFlops(fp32=3.55*TFLOPS, fp16=7.10*TFLOPS, int8=14.20*TFLOPS),
   "Apple M3 Pro": DeviceFlops(fp32=4.97*TFLOPS, fp16=9.94*TFLOPS, int8=19.88*TFLOPS),
   "Apple M3 Max": DeviceFlops(fp32=14.20*TFLOPS, fp16=28.40*TFLOPS, int8=56.80*TFLOPS),
+  "Apple M3 Ultra": DeviceFlops(fp32=54.26*TFLOPS, fp16=108.52*TFLOPS, int8=217.04*TFLOPS),
   "Apple M4": DeviceFlops(fp32=4.26*TFLOPS, fp16=8.52*TFLOPS, int8=17.04*TFLOPS),
   "Apple M4 Pro": DeviceFlops(fp32=5.72*TFLOPS, fp16=11.44*TFLOPS, int8=22.88*TFLOPS),
   "Apple M4 Max": DeviceFlops(fp32=18.03*TFLOPS, fp16=36.07*TFLOPS, int8=72.14*TFLOPS),