fix: skip cooperative top-K on SM120 (#47164)
Signed-off-by: Zihua Wu <13583761+lucifer1004@users.noreply.github.com>
This commit is contained in:
@@ -578,6 +578,7 @@ def sparse_attn_indexer(
|
|||||||
and num_rows <= 32
|
and num_rows <= 32
|
||||||
and logits.stride(0) % 4 == 0 # TMA 16-byte alignment
|
and logits.stride(0) % 4 == 0 # TMA 16-byte alignment
|
||||||
and current_platform.has_device_capability(90)
|
and current_platform.has_device_capability(90)
|
||||||
|
and not current_platform.is_device_capability_family(120)
|
||||||
)
|
)
|
||||||
use_persistent_topk = current_platform.is_cuda() and topk_tokens in (
|
use_persistent_topk = current_platform.is_cuda() and topk_tokens in (
|
||||||
512,
|
512,
|
||||||
|
|||||||
Reference in New Issue
Block a user