Revert D69257102: Unify cuBLASLt workspaces with cuBLAS workspaces (#145130)

Differential Revision:
D69257102

Original commit changeset: 4a2e6391fa89

Original Phabricator Diff: D69257102

fbshipit-source-id: 6fb20e28aafa38376b586e55782bdac72c45f890

Author: atalman

userbenchmark/dynamo/dynamobench/common.py

@@ -3563,15 +3563,6 @@ def run(runner, args, original_dir=None):
             # some of the models do not support use_deterministic_algorithms
             torch.use_deterministic_algorithms(True)
         os.environ["CUBLAS_WORKSPACE_CONFIG"] = ":4096:8"
-        if args.only is not None and args.only in {
-            "DebertaForQuestionAnswering",
-            "RobertaForQuestionAnswering",
-            "nvidia_deeprecommender",
-            "volo_d1_224",
-        }:
-            # These seem unhappy with numerics of larger cuBLASLt workspace
-            # sizes following #145130 (due to enabling split-k?)
-            torch.backends.cuda.matmul.allow_fp16_reduced_precision_reduction = False
         torch.backends.cudnn.deterministic = True
         torch.backends.cudnn.allow_tf32 = False
         torch.backends.cudnn.benchmark = False