↓ 1 callersMethod__init__(
self, B_in_hidden_out_ft: Tuple[int, int, int, int], dtype, bias: bool, bw: bool
)
xformers/benchmarks/benchmark_sp24.py:46
↓ 1 callersFunction_create_blocksparse_tensor(
device, block_size=32, Z=8, C=2, H=64, W=64, dtype=torch.float32
)
tests/test_sparse_tensors.py:23
↓ 1 callersFunction_merge_attentions_ref attn_split: [split_k, B, M, (G,) H, Kq] lse_split: [split_k, B, (G,) H, M]
tests/test_fmha_merge_attentions.py:513
↓ 1 callersFunction_merge_attentions_varargs_ref attn_split: list of [B, M, (G,) H, Kq] lse_split: list of [B, (G,) H, M]
xformers/benchmarks/benchmark_merge_attentions.py:12
↓ 1 callersFunction_overlap_fw_bw(
trigger_fw: Callable[[], T],
trigger_bw: Callable[[], None],
initial_bw_chunks: int = 0,
)
xformers/fwbw_overlap.py:508
↓ 1 callersFunction_pack_xformer_input(
q: torch.Tensor,
k: torch.Tensor,
v: torch.Tensor,
cache_seqlens: List[int],
bias_type,
tests/test_mem_eff_attention.py:2949