Support FP8 Per Token Quant Piecewise

[hebiao064]

Motivation

Before:

torch._dynamo.exc.Unsupported: Operator does not support running with fake tensors
  Explanation: 
  Hint: see https://docs.google.com/document/d/1GgvOe7C8_NVOMLOCwDaYV1mXXyHMXY7ExoewHqooxrs/edit#heading=h.64r4npvq0w0 for how to fix

  Developer debug context: unsupported operator: sgl_kernel.fp8_scaled_mm.default

After:

Accuracy: 0.950
Invalid: 0.000
Latency: 5.825 s
Output throughput: 4113.731 token/s

Modifications

Accuracy Tests

Benchmarking and Profiling

Checklist

• Format your code according to the Format code with pre-commit.
• Add unit tests according to the Run and add unit tests.
• Update documentation according to Write documentations.
• Provide accuracy and speed benchmark results according to Test the accuracy and Benchmark the speed.

[gemini-code-assist]

Warning

You have reached your daily quota limit. Please wait up to 24 hours and I will start processing your requests again!

[BBuf]

LGTM.