(num_output_tokens: int, generation_tps: float, acceptance_lengths: list[int])
| 110 | |
| 111 | |
| 112 | def _make_decode_metrics(num_output_tokens: int, generation_tps: float, acceptance_lengths: list[int]) -> SimpleNamespace: |
| 113 | return SimpleNamespace( |
| 114 | num_output_tokens=num_output_tokens, |
| 115 | time_per_output_token=1.0 / generation_tps if generation_tps > 0 else float("inf"), |
| 116 | acceptance_lengths=acceptance_lengths, |
| 117 | ) |
| 118 | |
| 119 | |
| 120 | def _print_decode_summary(responses: list[dict[int, SimpleNamespace]], block_size: int) -> None: |