iter_model_names() — pytorch Function Reference

Architecture documentation for the iter_model_names() function in huggingface.py from the pytorch codebase.

Function python DynamoBenchmarks Microbenchmarking calls 1

Entity Profile

DynamoBenchmarks→ Microbenchmarking→ iter_model_names() — pytorch Function Reference

Dependency Diagram

graph TD
  a022c1fd_0072_4493_ca52_f1e989604c2c["iter_model_names()"]
  e9a82af3_ba81_409b_9d46_c9e701ace22a["get_benchmark_indices()"]
  a022c1fd_0072_4493_ca52_f1e989604c2c -->|calls| e9a82af3_ba81_409b_9d46_c9e701ace22a
  style a022c1fd_0072_4493_ca52_f1e989604c2c fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

benchmarks/dynamo/huggingface.py lines 495–511

    def iter_model_names(self, args):
        model_names = list(BATCH_SIZE_KNOWN_MODELS.keys()) + list(EXTRA_MODELS.keys())
        model_names = set(model_names)
        model_names = sorted(model_names)

        start, end = self.get_benchmark_indices(len(model_names))
        for index, model_name in enumerate(model_names):
            if index < start or index >= end:
                continue
            if (
                not re.search("|".join(args.filter), model_name, re.IGNORECASE)
                or re.search("|".join(args.exclude), model_name, re.IGNORECASE)
                or model_name in args.exclude_exact
                or model_name in self.skip_models
            ):
                continue
            yield model_name