From 3ba920a65be86bef5252af7433e601725a36e029 Mon Sep 17 00:00:00 2001 From: jiangyunfan1 Date: Mon, 22 Dec 2025 18:54:03 +0800 Subject: [PATCH] [TEST]Update mm param --mm-processor-cache-gb (#5242) ### What this PR does / why we need it? This PR updates the mm param --mm-processor-cache-gb, we need it to run the case ### Does this PR introduce _any_ user-facing change? No ### How was this patch tested? by running the test - vLLM version: release/v0.13.0 - vLLM main: https://github.com/vllm-project/vllm/commit/ad32e3e19ccf0526cb6744a5fed09a138a5fb2f9 Signed-off-by: jiangyunfan1 --- tests/e2e/nightly/models/test_qwen2_5_vl_32b.py | 2 +- tests/e2e/nightly/models/test_qwen2_5_vl_7b.py | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/tests/e2e/nightly/models/test_qwen2_5_vl_32b.py b/tests/e2e/nightly/models/test_qwen2_5_vl_32b.py index 77c1a7e1..4ecd403f 100644 --- a/tests/e2e/nightly/models/test_qwen2_5_vl_32b.py +++ b/tests/e2e/nightly/models/test_qwen2_5_vl_32b.py @@ -80,7 +80,7 @@ async def test_models(model: str, tp_size: int) -> None: "HCCL_OP_EXPANSION_MODE": "AIV" } server_args = [ - "--no-enable-prefix-caching", "--disable-mm-preprocessor-cache", + "--no-enable-prefix-caching", "--mm-processor-cache-gb", "0", "--tensor-parallel-size", str(tp_size), "--port", str(port), "--max-model-len", "30000", "--max-num-batched-tokens", diff --git a/tests/e2e/nightly/models/test_qwen2_5_vl_7b.py b/tests/e2e/nightly/models/test_qwen2_5_vl_7b.py index d3a726bf..33cab210 100644 --- a/tests/e2e/nightly/models/test_qwen2_5_vl_7b.py +++ b/tests/e2e/nightly/models/test_qwen2_5_vl_7b.py @@ -72,7 +72,7 @@ async def test_models(model: str, tp_size: int) -> None: "HCCL_OP_EXPANSION_MODE": "AIV" } server_args = [ - "--no-enable-prefix-caching", "--disable-mm-preprocessor-cache", + "--no-enable-prefix-caching", "--mm-processor-cache-gb", "0", "--tensor-parallel-size", str(tp_size), "--port", str(port), "--max-model-len", "30000", "--max-num-batched-tokens",