Skip to content

rename is_b200 to is_blackwell #646

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Nov 15, 2025
Merged

rename is_b200 to is_blackwell #646

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 5 additions & 3 deletions tritonbench/operators/blackwell_attentions/operator.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -120,7 +120,9 @@
torch.cuda.is_available() and torch.version.cuda and torch.version.cuda >= "12.4"
)

IS_B200 = is_cuda() and "B200" in get_nvidia_gpu_model()
IS_BLACKWELL = is_cuda() and (
"B200" in get_nvidia_gpu_model() or "B300" in get_nvidia_gpu_model()
)


def parse_op_args(args: List[str]):
Expand Down Expand Up @@ -385,7 +387,7 @@ def xformers_splitk(
)

@register_benchmark(
enabled=IS_B200 and _is_sdpa_cudnn_attention_available(),
enabled=IS_BLACKWELL and _is_sdpa_cudnn_attention_available(),
label=f"cudnn-sdpa-{torch.backends.cudnn.version()}",
)
def cudnn_sdpa(self, q, k, v):
Expand All @@ -398,7 +400,7 @@ def cudnn_sdpa(self, q, k, v):
)

@register_benchmark(
enabled=(IS_B200 and HAS_FLASH_CUTE), label="FAv4", fwd_only=True
enabled=(IS_BLACKWELL and HAS_FLASH_CUTE), label="FAv4", fwd_only=True
)
def cutedsl_blackwell(
self, q: torch.Tensor, k: torch.Tensor, v: torch.Tensor
Expand Down
Loading