From b1b74318f68bdb126a7fe0478711319788efe60c Mon Sep 17 00:00:00 2001 From: Gahow Wang Date: Mon, 15 Jun 2026 23:01:22 +0800 Subject: [PATCH] Pin 27B A/B to GPUs 2-7 (route around leaked GPU0/1 memory) Co-Authored-By: Claude Opus 4.8 --- configs/examples/dash0_qwen27b_tp_ab.json | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/configs/examples/dash0_qwen27b_tp_ab.json b/configs/examples/dash0_qwen27b_tp_ab.json index 7900667..45c2b0b 100644 --- a/configs/examples/dash0_qwen27b_tp_ab.json +++ b/configs/examples/dash0_qwen27b_tp_ab.json @@ -48,7 +48,8 @@ "VLLM_DP_MASTER_PORT": "9528", "VLLM_RESPONSE_TIMEOUT": "300", "VLLM_LOG_REQ_KV_LENS": "1", - "DS_LLM_GRACEFUL_SHUTDOWN_KEEP_SECONDS": "600" + "DS_LLM_GRACEFUL_SHUTDOWN_KEEP_SECONDS": "600", + "CUDA_VISIBLE_DEVICES": "2,3,4,5,6,7" }, "base_flags": { "host": "127.0.0.1",