From 1b1207e3c360b2875d275afbaedcb3971415a8d4 Mon Sep 17 00:00:00 2001 From: Li Wang Date: Sat, 11 Oct 2025 19:25:16 +0800 Subject: [PATCH] [Bugfix] Add quantization param for multi-node CI (#3383) ### What this PR does / why we need it? Add quantization param for `deepseek-w8a8` multi-node test ### Does this PR introduce _any_ user-facing change? ### How was this patch tested? - vLLM version: v0.11.0rc3 - vLLM main: https://github.com/vllm-project/vllm/commit/v0.11.0 Signed-off-by: wangli --- tests/e2e/multi_node/config/config.json | 2 ++ 1 file changed, 2 insertions(+) diff --git a/tests/e2e/multi_node/config/config.json b/tests/e2e/multi_node/config/config.json index 465f92c..2954881 100644 --- a/tests/e2e/multi_node/config/config.json +++ b/tests/e2e/multi_node/config/config.json @@ -7,6 +7,7 @@ "server_parameters": { "leader_config": { "model": "vllm-ascend/DeepSeek-V3-W8A8", + "quantization": "ascend", "additional_config": { "ascend_scheduler_config": { "enabled": true @@ -18,6 +19,7 @@ }, "worker_config": { "model": "vllm-ascend/DeepSeek-V3-W8A8", + "quantization": "ascend", "additional_config": { "ascend_scheduler_config": { "enabled": true