From 6b6857929d8397fbec1cd132eb4ea5d13712497c Mon Sep 17 00:00:00 2001 From: likeful Date: Mon, 20 Oct 2025 23:37:35 +0800 Subject: [PATCH] [Doc] Add --shm-size option to Docker command for qwen3 vl 235B (#3519) ### What this PR does / why we need it? Added shared memory size option to Docker run command.If shm-size is not specified, docker will use 64MB by default. In this case, vllm:EngineCore process may coredump if workload is high. ### Does this PR introduce _any_ user-facing change? No ### How was this patch tested? Done Closes: https://github.com/vllm-project/vllm-ascend/issues/3513 - vLLM version: v0.11.0rc3 - vLLM main: https://github.com/vllm-project/vllm/commit/v0.11.0 --------- Signed-off-by: likeful Signed-off-by: leijie2015 Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> --- docs/source/tutorials/multi_node_qwen3vl.md | 1 + 1 file changed, 1 insertion(+) diff --git a/docs/source/tutorials/multi_node_qwen3vl.md b/docs/source/tutorials/multi_node_qwen3vl.md index 18d063d..4ebedfa 100644 --- a/docs/source/tutorials/multi_node_qwen3vl.md +++ b/docs/source/tutorials/multi_node_qwen3vl.md @@ -37,6 +37,7 @@ docker run --rm \ --device /dev/davinci_manager \ --device /dev/devmm_svm \ --device /dev/hisi_hdc \ +--shm-size 256g \ -v /usr/local/dcmi:/usr/local/dcmi \ -v /usr/local/Ascend/driver/tools/hccn_tool:/usr/local/Ascend/driver/tools/hccn_tool \ -v /usr/local/bin/npu-smi:/usr/local/bin/npu-smi \