From fe15729a2b77d760fcf99da76f15806c5eab33df Mon Sep 17 00:00:00 2001 From: Woosuk Kwon Date: Mon, 11 Nov 2024 11:26:48 -0800 Subject: [PATCH] [V1] Use custom ops for piecewise CUDA graphs (#10227) Signed-off-by: Woosuk Kwon --- vllm/v1/worker/gpu_model_runner.py | 2 -- 1 file changed, 2 deletions(-) diff --git a/vllm/v1/worker/gpu_model_runner.py b/vllm/v1/worker/gpu_model_runner.py index 1e20920d14432..74a7b4caa6b16 100644 --- 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,