From e26fe1caf1cc15fe430ede2a210b5612d8872619 Mon Sep 17 00:00:00 2001 From: zhangxinyuehfad <59153331+zhangxinyuehfad@users.noreply.github.com> Date: Sat, 20 Sep 2025 00:40:33 +0800 Subject: [PATCH] [TEST] Speed up DS V2 accuracy test and turn up accuracy baseline (#3047) ### What this PR does / why we need it? 1. update expected accuracy for DeepSeek-V2-Lite 2. add batch size ### Does this PR introduce _any_ user-facing change? No ### How was this patch tested? Accuracy CI passed - vLLM version: v0.10.2 - vLLM main: https://github.com/vllm-project/vllm/commit/838d7116ba59db528647b29f0d000742f4af9d4b Signed-off-by: hfadzxy --- tests/e2e/models/configs/DeepSeek-V2-Lite.yaml | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/tests/e2e/models/configs/DeepSeek-V2-Lite.yaml b/tests/e2e/models/configs/DeepSeek-V2-Lite.yaml index 571a2e4..e4adbde 100644 --- a/tests/e2e/models/configs/DeepSeek-V2-Lite.yaml +++ b/tests/e2e/models/configs/DeepSeek-V2-Lite.yaml @@ -3,11 +3,11 @@ tasks: - name: "gsm8k" metrics: - name: "exact_match,strict-match" - value: 0.375 + value: 0.385 - name: "exact_match,flexible-extract" - value: 0.375 + value: 0.385 tensor_parallel_size: 2 -batch_size: 8 +batch_size: 32 gpu_memory_utilization: 0.7 apply_chat_template: False fewshot_as_multiturn: False