Fix memory leak when doing chunked prefill (#1787)

2024-10-25 08:01:17 -07:00
parent 2148914e1b
commit a2f5e7555f
7 changed files with 184 additions and 69 deletions
--- a/test/srt/run_suite.py
+++ b/test/srt/run_suite.py
@@ -5,6 +5,7 @@ from sglang.test.test_utils import run_unittest_files

 suites = {
    "minimal": [
+        "test_radix_attention.py",
        "models/test_embedding_models.py",
        "models/test_generation_models.py",
        "models/test_lora.py",