[V1] Use custom ops for piecewise CUDA graphs (vllm-project#10227)

Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
drikster80 · Nov 11, 2024 · fe15729 · fe15729
1 parent 330e82d
commit fe15729
Showing 1 changed file with 0 additions and 2 deletions.
diff --git a/vllm/v1/worker/gpu_model_runner.py b/vllm/v1/worker/gpu_model_runner.py
@@ -1,4 +1,3 @@
-import os
 import time
 from dataclasses import dataclass
 from typing import TYPE_CHECKING, Dict, List, Optional, Set
@@ -406,7 +405,6 @@ def load_model(self) -> None:
         if self.use_cuda_graph:
             # FIXME(woosuk): Currently, we do not use inductor to reduce the
             # compilation time and any potential issues with the inductor.
-            os.environ["VLLM_CUSTOM_OPS"] = "none"
             set_compilation_config(
                 CompilationConfig(
                     use_cudagraph=True,