Delete PagedAttention (#47361)
Signed-off-by: mgoin <mgoin64@gmail.com>
This commit is contained in:
@@ -117,100 +117,6 @@ if hasattr(torch.ops, "_C") and hasattr(torch.ops._C, "scaled_fp4_quant"):
|
||||
|
||||
|
||||
# page attention ops
|
||||
def paged_attention_v1(
|
||||
out: torch.Tensor,
|
||||
query: torch.Tensor,
|
||||
key_cache: torch.Tensor,
|
||||
value_cache: torch.Tensor,
|
||||
num_kv_heads: int,
|
||||
scale: float,
|
||||
block_tables: torch.Tensor,
|
||||
seq_lens: torch.Tensor,
|
||||
block_size: int,
|
||||
max_seq_len: int,
|
||||
alibi_slopes: torch.Tensor | None,
|
||||
kv_cache_dtype: str,
|
||||
k_scale: torch.Tensor,
|
||||
v_scale: torch.Tensor,
|
||||
tp_rank: int = 0,
|
||||
blocksparse_local_blocks: int = 0,
|
||||
blocksparse_vert_stride: int = 0,
|
||||
blocksparse_block_size: int = 64,
|
||||
blocksparse_head_sliding_step: int = 0,
|
||||
) -> None:
|
||||
torch.ops._C.paged_attention_v1(
|
||||
out,
|
||||
query,
|
||||
key_cache,
|
||||
value_cache,
|
||||
num_kv_heads,
|
||||
scale,
|
||||
block_tables,
|
||||
seq_lens,
|
||||
block_size,
|
||||
max_seq_len,
|
||||
alibi_slopes,
|
||||
kv_cache_dtype,
|
||||
k_scale,
|
||||
v_scale,
|
||||
tp_rank,
|
||||
blocksparse_local_blocks,
|
||||
blocksparse_vert_stride,
|
||||
blocksparse_block_size,
|
||||
blocksparse_head_sliding_step,
|
||||
)
|
||||
|
||||
|
||||
def paged_attention_v2(
|
||||
out: torch.Tensor,
|
||||
exp_sum: torch.Tensor,
|
||||
max_logits: torch.Tensor,
|
||||
tmp_out: torch.Tensor,
|
||||
query: torch.Tensor,
|
||||
key_cache: torch.Tensor,
|
||||
value_cache: torch.Tensor,
|
||||
num_kv_heads: int,
|
||||
scale: float,
|
||||
block_tables: torch.Tensor,
|
||||
seq_lens: torch.Tensor,
|
||||
block_size: int,
|
||||
max_seq_len: int,
|
||||
alibi_slopes: torch.Tensor | None,
|
||||
kv_cache_dtype: str,
|
||||
k_scale: torch.Tensor,
|
||||
v_scale: torch.Tensor,
|
||||
tp_rank: int = 0,
|
||||
blocksparse_local_blocks: int = 0,
|
||||
blocksparse_vert_stride: int = 0,
|
||||
blocksparse_block_size: int = 64,
|
||||
blocksparse_head_sliding_step: int = 0,
|
||||
) -> None:
|
||||
torch.ops._C.paged_attention_v2(
|
||||
out,
|
||||
exp_sum,
|
||||
max_logits,
|
||||
tmp_out,
|
||||
query,
|
||||
key_cache,
|
||||
value_cache,
|
||||
num_kv_heads,
|
||||
scale,
|
||||
block_tables,
|
||||
seq_lens,
|
||||
block_size,
|
||||
max_seq_len,
|
||||
alibi_slopes,
|
||||
kv_cache_dtype,
|
||||
k_scale,
|
||||
v_scale,
|
||||
tp_rank,
|
||||
blocksparse_local_blocks,
|
||||
blocksparse_vert_stride,
|
||||
blocksparse_block_size,
|
||||
blocksparse_head_sliding_step,
|
||||
)
|
||||
|
||||
|
||||
def paged_attention_rocm(
|
||||
out: torch.Tensor,
|
||||
exp_sum: torch.Tensor,
|
||||
|
||||
Reference in New Issue
Block a user