./format.sh

Signed-off-by: Harry Mellor <[email protected]>

Author: hmellor

docs/source/generate_examples.py

@@ -132,7 +132,8 @@ def generate(self) -> str:
             ROOT_DIR)
 
         content = f"Source <gh-file:{self.path.relative_to(ROOT_DIR)}>.\n\n"
-        include = "include" if self.main_file.suffix == ".md" else "literalinclude"
+        include = "include" if self.main_file.suffix == ".md" else \
+            "literalinclude"
         if include == "literalinclude":
             content += f"# {self.title}\n\n"
         content += f":::{{{include}}} {make_relative(self.main_file)}\n"

tools/profiler/visualize_layerwise_profile.py

@@ -534,11 +534,11 @@ def make_plot_title_suffix(profile_json: dict) -> str:
 if __name__ == "__main__":
     parser = argparse.ArgumentParser()
 
-    parser.add_argument(
-        "--json-trace",
-        type=str,
-        required=True,
-        help="json trace file output by examples/offline_inference/offline_profile.py")
+    parser.add_argument("--json-trace",
+                        type=str,
+                        required=True,
+                        help="json trace file output by \
+                              examples/offline_inference/offline_profile.py")
     parser.add_argument("--output-directory",
                         type=str,
                         required=False,

vllm/model_executor/model_loader/loader.py

@@ -529,7 +529,8 @@ class ShardedStateLoader(BaseModelLoader):
     Model loader that directly loads each worker's model state dict, which
     enables a fast load path for large tensor-parallel models where each worker
     only needs to read its own shard rather than the entire checkpoint. See
-    `examples/offline_inference/save_sharded_state.py` for creating a sharded checkpoint.
+    `examples/offline_inference/save_sharded_state.py` for creating a sharded
+    checkpoint.
     """
 
     DEFAULT_PATTERN = "model-rank-{rank}-part-{part}.safetensors"

vllm/model_executor/model_loader/tensorizer.py

@@ -363,13 +363,12 @@ def deserialize(self):
 def tensorizer_weights_iterator(
     tensorizer_args: "TensorizerArgs"
 ) -> Generator[Tuple[str, torch.Tensor], None, None]:
-    logger.warning(
-        "Deserializing HuggingFace models is not optimized for "
-        "loading on vLLM, as tensorizer is forced to load to CPU. "
-        "Consider deserializing a vLLM model instead for faster "
-        "load times. See the "
-        "examples/other/tensorize_vllm_model.py example script "
-        "for serializing vLLM models.")
+    logger.warning("Deserializing HuggingFace models is not optimized for "
+                   "loading on vLLM, as tensorizer is forced to load to CPU. "
+                   "Consider deserializing a vLLM model instead for faster "
+                   "load times. See the "
+                   "examples/other/tensorize_vllm_model.py example script "
+                   "for serializing vLLM models.")
 
     deserializer_args = tensorizer_args.deserializer_params
     stream_params = tensorizer_args.stream_params

vllm/model_executor/model_loader/weight_utils.py

@@ -503,7 +503,8 @@ def kv_cache_scales_loader(
     KV cache scaling factors. The serialization should represent a dictionary
     whose keys are the TP ranks and values are another dictionary mapping layers
     to their KV cache scaling factors.
-    Keep this function in sync with the output of examples/other/fp8/extract_scales.py
+    Keep this function in sync with the output of
+    examples/other/fp8/extract_scales.py
     """
     try:
         with open(filename) as f: