From 3b47973af8474ff913de82c2837ddd54c3ad7631 Mon Sep 17 00:00:00 2001 From: b8zhong Date: Sun, 7 Dec 2025 13:30:41 -0800 Subject: [PATCH] [CI] Tiny speed up VLM CI (#14517) Co-authored-by: Brayden Zhong --- python/sglang/test/mmmu_vlm_mixin.py | 4 ++-- test/srt/models/test_vlm_models.py | 2 +- test/srt/run_suite.py | 4 ++-- 3 files changed, 5 insertions(+), 5 deletions(-) diff --git a/python/sglang/test/mmmu_vlm_mixin.py b/python/sglang/test/mmmu_vlm_mixin.py index e621a0087..c4c739f15 100644 --- a/python/sglang/test/mmmu_vlm_mixin.py +++ b/python/sglang/test/mmmu_vlm_mixin.py @@ -53,7 +53,7 @@ class MMMUVLMMixin(ABC): model = "openai_compatible" tp = 1 tasks = "mmmu_val" - batch_size = 32 + batch_size = 64 log_suffix = "openai_compatible" os.makedirs(output_path, exist_ok=True) @@ -137,7 +137,7 @@ class MMMUVLMMixin(ABC): other_args=[ "--trust-remote-code", "--cuda-graph-max-bs", - "32", + "64", "--enable-multimodal", "--mem-fraction-static", str(self.parsed_args.mem_fraction_static), # Use class variable diff --git a/test/srt/models/test_vlm_models.py b/test/srt/models/test_vlm_models.py index b26ff0831..3650621a5 100644 --- a/test/srt/models/test_vlm_models.py +++ b/test/srt/models/test_vlm_models.py @@ -14,7 +14,7 @@ if _is_hip: MODELS = [SimpleNamespace(model="openbmb/MiniCPM-V-2_6", mmmu_accuracy=0.4)] else: MODELS = [ - SimpleNamespace(model="google/gemma-3-27b-it", mmmu_accuracy=0.45), + SimpleNamespace(model="google/gemma-3-4b-it", mmmu_accuracy=0.38), SimpleNamespace(model="Qwen/Qwen2.5-VL-3B-Instruct", mmmu_accuracy=0.4), SimpleNamespace(model="openbmb/MiniCPM-V-2_6", mmmu_accuracy=0.4), ] diff --git a/test/srt/run_suite.py b/test/srt/run_suite.py index 3a36836cf..5175f3524 100644 --- a/test/srt/run_suite.py +++ b/test/srt/run_suite.py @@ -29,7 +29,7 @@ suites = { TestFile("models/test_qwen_models.py", 90), TestFile("models/test_reward_models.py", 103), TestFile("models/test_transformers_models.py", 245), - TestFile("models/test_vlm_models.py", 282), + TestFile("models/test_vlm_models.py", 270), TestFile("openai_server/basic/test_openai_embedding.py", 70), TestFile("openai_server/basic/test_openai_server.py", 184), TestFile("openai_server/basic/test_protocol.py", 3), @@ -237,7 +237,7 @@ suite_amd = { TestFile("models/test_qwen_models.py", 82), TestFile("models/test_reward_models.py", 132), TestFile("models/test_transformers_models.py", 320), - TestFile("models/test_vlm_models.py", 437), + TestFile("models/test_vlm_models.py", 387), TestFile("openai_server/basic/test_openai_embedding.py", 141), TestFile("openai_server/basic/test_openai_server.py", 149), TestFile("openai_server/basic/test_protocol.py", 10),