We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
1 parent bb14aa5 commit b23d937Copy full SHA for b23d937
tritonbench/operators/decoding_attention/operator.py
@@ -277,6 +277,7 @@ class Operator(BenchmarkOperator):
277
DEFAULT_PRECISION = "bf16"
278
279
DEFAULT_METRICS = ["latency", "speedup"]
280
+ FWD_ONLY = True
281
282
def __init__(
283
self, tb_args: argparse.Namespace, extra_args: Optional[List[str]] = None
0 commit comments