Warn users when release_memory_occupation is called without memory saver enabled (#4566)

python/sglang/test/attention/test_flashattn_backend.py

@@ -6,6 +6,7 @@ from sglang.srt.layers.attention.flashattention_backend import FlashAttentionBac
 from sglang.srt.layers.radix_attention import RadixAttention
 from sglang.srt.mem_cache.memory_pool import MHATokenToKVPool
 from sglang.srt.model_executor.forward_batch_info import ForwardBatch, ForwardMode
+from sglang.test.test_utils import CustomTestCase
 
 
 class MockModelRunner:
@@ -39,7 +40,7 @@ class MockReqToTokenPool:
 
 
 @unittest.skipIf(not torch.cuda.is_available(), "Test requires CUDA")
-class TestFlashAttentionBackend(unittest.TestCase):
+class TestFlashAttentionBackend(CustomTestCase):
     def setUp(self):
         """Set up test fixtures before each test method."""
         self.model_runner = MockModelRunner()

python/sglang/test/test_utils.py

@@ -3,6 +3,7 @@
 import argparse
 import asyncio
 import copy
+import logging
 import os
 import random
 import subprocess
@@ -922,6 +923,10 @@ def run_mulit_request_test(
 
 
 def write_github_step_summary(content):
+    if not os.environ.get("GITHUB_STEP_SUMMARY"):
+        logging.warning("GITHUB_STEP_SUMMARY environment variable not set")
+        return
+
     with open(os.environ["GITHUB_STEP_SUMMARY"], "a") as f:
         f.write(content)