From b1488ecdb1be1a4bacc1b4c6920b06b69c3154fa Mon Sep 17 00:00:00 2001 From: pz1116 <47019764+Pz1116@users.noreply.github.com> Date: Wed, 5 Nov 2025 18:39:35 +0800 Subject: [PATCH] [main][doc][kv_pool]Add adxl timeout parameter in kv pool user guide (#4012) ### What this PR does / why we need it? Add adxl timeout parameter in kv pool user guide, avoiding timeout error when initializing connections between devices. - vLLM version: v0.11.0 - vLLM main: https://github.com/vllm-project/vllm/commit/83f478bb19489b41e9d208b47b4bb5a95ac171ac Signed-off-by: Pz1116 --- docs/source/user_guide/feature_guide/kv_pool_mooncake.md | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/docs/source/user_guide/feature_guide/kv_pool_mooncake.md b/docs/source/user_guide/feature_guide/kv_pool_mooncake.md index 6bb0e130..a9c61cd1 100644 --- a/docs/source/user_guide/feature_guide/kv_pool_mooncake.md +++ b/docs/source/user_guide/feature_guide/kv_pool_mooncake.md @@ -87,6 +87,8 @@ export ASCEND_RT_VISIBLE_DEVICES=0,1,2,3 export ACL_OP_INIT_MODE=1 export ASCEND_BUFFER_POOL=4:8 # ASCEND_BUFFER_POOL is the environment variable for configuring the number and size of buffer on NPU Device for aggregation and KV transfer，the value 4:8 means we allocate 4 buffers of size 8MB. +export ASCEND_CONNECT_TIMEOUT=10000 +export ASCEND_TRANSFER_TIMEOUT=10000 python3 -m vllm.entrypoints.openai.api_server \ --model /xxxxx/Qwen2.5-7B-Instruct \ @@ -147,6 +149,8 @@ export VLLM_USE_V1=1 export ASCEND_RT_VISIBLE_DEVICES=4,5,6,7 export ACL_OP_INIT_MODE=1 export ASCEND_BUFFER_POOL=4:8 +export ASCEND_CONNECT_TIMEOUT=10000 +export ASCEND_TRANSFER_TIMEOUT=10000 python3 -m vllm.entrypoints.openai.api_server \ --model /xxxxx/Qwen2.5-7B-Instruct \ @@ -246,6 +250,8 @@ export VLLM_USE_V1=1 export ASCEND_RT_VISIBLE_DEVICES=0,1,2,3 export ACL_OP_INIT_MODE=1 export ASCEND_BUFFER_POOL=4:8 +export ASCEND_CONNECT_TIMEOUT=10000 +export ASCEND_TRANSFER_TIMEOUT=10000 python3 -m vllm.entrypoints.openai.api_server \ --model /xxxxx/Qwen2.5-7B-Instruct \