flashinfer.testing.attention_tflops_per_sec_with_actual_seq_lens

flashinfer.testing.attention_tflops_per_sec_with_actual_seq_lens(actual_seq_lens_q, actual_seq_lens_kv, head_dim_qk, head_dim_vo, num_qo_heads, causal, time)

Calculate TFLOPS per second for a given attention layer with actual sequence lengths. Does not assume all sequence lengths are the same within the batch.

Parameters:

  • actual_seq_lens_q (torch.Tensor) – Array of actual sequence lengths of the query.

  • actual_seq_lens_kv (torch.Tensor) – Array of actual sequence lengths of the key and value.

  • head_dim_qk (int) – Head dimension of the query and key.

  • head_dim_vo (int) – Head dimension of the value.

  • num_qo_heads (int) – Number of query heads.

  • causal (bool) – Whether to use causal masking.

  • time (float) – Execution time in milliseconds.

Returns:

TFLOPS per second for the layer.

Return type:

tflops_per_sec (float)