[CI] Tiny speed up VLM CI (#14517)

Co-authored-by: Brayden Zhong <b8zhong@users.noreply.github.com>

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

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),
     ]

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),