Enhance the test case for chunked prefill (#1785)

2024-10-24 21:23:09 -07:00
parent 384d85ba35
commit 1701b0db31
6 changed files with 162 additions and 107 deletions
--- a/test/srt/run_suite.py
+++ b/test/srt/run_suite.py
@@ -15,7 +15,7 @@ suites = {
        "test_embedding_openai_server.py",
        "test_eval_accuracy_mini.py",
        "test_json_constrained.py",
-        # "test_large_max_new_tokens.py",  # This test hangs on CI due to unknown reasons
+        "test_large_max_new_tokens.py",
        "test_openai_server.py",
        "test_overlap_schedule.py",
        "test_pytorch_sampling_backend.py",