diff --git a/vllm_ascend/patch/platform/__init__.py b/vllm_ascend/patch/platform/__init__.py index 42d86a3..60788eb 100644 --- a/vllm_ascend/patch/platform/__init__.py +++ b/vllm_ascend/patch/platform/__init__.py @@ -25,6 +25,6 @@ if os.getenv("DYNAMIC_EPLB", "false") == "true" or os.getenv( "EXPERT_MAP_RECORD", "false") == "true": import vllm_ascend.patch.platform.patch_multiproc_executor # noqa -if os.getenv("SHM_BARRIER", "false") == "true": +if os.getenv("SHM_BARRIER", "true") == "true": import vllm_ascend.patch.platform.patch_core # noqa import vllm_ascend.patch.platform.patch_message_queue # noqa diff --git a/vllm_ascend/patch/worker/__init__.py b/vllm_ascend/patch/worker/__init__.py index 50088f3..8d20647 100644 --- a/vllm_ascend/patch/worker/__init__.py +++ b/vllm_ascend/patch/worker/__init__.py @@ -15,6 +15,8 @@ # limitations under the License. # +import os + from vllm.triton_utils import HAS_TRITON if HAS_TRITON: @@ -29,4 +31,7 @@ import vllm_ascend.patch.worker.patch_weight_loader # noqa import vllm_ascend.patch.worker.patch_multimodal_merge # noqa import vllm_ascend.patch.worker.patch_minicpm # noqa import vllm_ascend.patch.worker.patch_deepseek_mtp # noqa -import vllm_ascend.patch.worker.patch_attention_layer # noqa \ No newline at end of file +import vllm_ascend.patch.worker.patch_attention_layer # noqa + +if os.getenv("SHM_BARRIER", "true") == "true": + import vllm_ascend.patch.platform.patch_message_queue # noqa