From 52abd47f8c5813556c2d5e7ab73ca09229174ef3 Mon Sep 17 00:00:00 2001 From: Zetong Li <48438720+slippersss@users.noreply.github.com> Date: Mon, 1 Dec 2025 22:27:01 +0800 Subject: [PATCH] [Bugfix][SHM] Use writer lock by default and remove redundant env (#4117) ### What this PR does / why we need it? This PR aims to remove env introduced by #3988 and use lock by default. As described in https://github.com/vllm-project/vllm/issues/27858, we have tested the writer lock method in various scenarios and the performance is almost unaffected. Therefore, we believe that it would be safe to enable the lock by default and remove the redundant env `SHM_BARRIER` now. After discussion, we decide to preserve env and set it as true by default. ### Does this PR introduce _any_ user-facing change? `SHM_BARRIER` is set as true by default. ### How was this patch tested? by ci --------- Signed-off-by: Zetong Li --- vllm_ascend/patch/platform/__init__.py | 2 +- vllm_ascend/patch/worker/__init__.py | 7 ++++++- 2 files changed, 7 insertions(+), 2 deletions(-) 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