Fix memory leak for chunked prefill 2 (#1858)

Co-authored-by: Liangsheng Yin <hnyls2002@gmail.com>
2024-10-31 14:51:51 -07:00
parent 8ce202a493
commit a2e0424abf
7 changed files with 138 additions and 30 deletions
--- a/test/srt/run_suite.py
+++ b/test/srt/run_suite.py
@@ -19,6 +19,7 @@ suites = {
        "test_openai_server.py",
        "test_overlap_schedule.py",
        "test_pytorch_sampling_backend.py",
+        "test_radix_attention.py",
        "test_retract_decode.py",
        "test_server_args.py",
        "test_skip_tokenizer_init.py",