format

Signed-off-by: Sage Moore <[email protected]>
vllm-project · Dec 6, 2024 · 774559d · 774559d
1 parent 553d99c
commit 774559d
Show file tree

Hide file tree

Showing 2 changed files with 13 additions and 9 deletions.
diff --git a/benchmarks/benchmark_latency.py b/benchmarks/benchmark_latency.py
@@ -70,7 +70,8 @@ def run_to_completion(profile_dir: Optional[str] = None):
         profile_dir = args.profile_result_dir
         if not profile_dir:
             profile_dir = Path(
-                ".") / "vllm_benchmark_result" / f"latency_result_{time.time()}"
+                "."
+            ) / "vllm_benchmark_result" / f"latency_result_{time.time()}"
         print(f"Profiling (results will be saved to '{profile_dir}')...")
         run_to_completion(profile_dir=profile_dir)
         return
@@ -117,19 +118,21 @@ def run_to_completion(profile_dir: Optional[str] = None):
                         type=int,
                         default=30,
                         help='Number of iterations to run.')
-    parser.add_argument('--profile',
-                        action='store_true',
-                        help='profile the generation process of a single batch')
+    parser.add_argument(
+        '--profile',
+        action='store_true',
+        help='profile the generation process of a single batch')
     parser.add_argument(
         '--profile-result-dir',
         type=str,
         default=None,
         help=('path to save the pytorch profiler output. Can be visualized '
               'with ui.perfetto.dev or Tensorboard.'))
-    parser.add_argument('--output-json',
-                        type=str,
-                        default=None,
-                        help='Path to save the latency results in JSON format.')
+    parser.add_argument(
+        '--output-json',
+        type=str,
+        default=None,
+        help='Path to save the latency results in JSON format.')
 
     parser = EngineArgs.add_cli_args(parser)
     args = parser.parse_args()

diff --git a/vllm/compilation/activation_quant_fusion.py b/vllm/compilation/activation_quant_fusion.py
@@ -98,7 +98,8 @@ def __call__(self, graph: torch.fx.Graph):
         self.dump_graph(graph, "before_act_quant_fusion")
 
         count = self.patterns.apply(graph)
-        logger.debug("Replaced %s patterns in ActivationQuantFusionPass", count)
+        logger.debug("Replaced %s patterns in ActivationQuantFusionPass",
+                     count)
         self.dump_graph(graph, "after_pattern_match")
 
         self.dump_graph(graph, "after_act_quant_fusion")