Run sampler as a method if available

[larryliu0820]

With this PR: huggingface/optimum-executorch#207 we are adding a new method "sampler" to ASR models, alongside with "encoder" and "text_decoder". The flow becomes: if temperature is 0 and sampler method is available, run that method. Otherwise still go with the old path. This change should largely improve the performance on CUDA since we don't have to copy logits from device to CPU for sampling purpose.

Benchmark result on RTX 5080:

======================================================================
BENCHMARK SUMMARY
======================================================================
Total runs: 30
Generated tokens per run: 104

THROUGHPUT (tokens/sec):
  Min:    793.89 t/s
  Max:    845.53 t/s
  Mean:   820.35 t/s
  Stdev:  11.86 t/s

MODEL LOAD TIME (ms):
  Min:    620 ms
  Max:    2170 ms
  Mean:   700 ms
  Stdev:  279 ms

ENCODE TIME (ms, inference_start to prompt_eval_end):
  Min:    36 ms
  Max:    38 ms
  Mean:   37 ms
  Stdev:  1 ms

DECODE TIME (ms, prompt_eval_end to inference_end):
  Min:    123 ms
  Max:    131 ms
  Mean:   127 ms
  Stdev:  2 ms

======================================================================

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/16888

• 📄 Preview Python docs built from this PR

Note: Links to docs will display an error until the docs builds have been completed.

⏳ No Failures, 21 Pending

As of commit ddb0dce with merge base e4060ee ():
💚 Looks good so far! There are no failures yet. 💚

This comment was automatically generated by Dr. CI and updates every 15 minutes.

[Gasoonjia]

Perf is crazy!! THanks for the great work!

And we now is still load generate token from gpu to cpu one by one right iiuc. if so the perf should be boost again after we use batch transfer!