[Frontend] Fix request length check and add option to disallow auto truncation in scheduler (#2876)

2025-01-16 14:51:19 -08:00
parent 0427416b59
commit a8ccacc8b8
6 changed files with 154 additions and 17 deletions
--- a/test/srt/run_suite.py
+++ b/test/srt/run_suite.py
@@ -31,6 +31,7 @@ suites = {
        "test_pytorch_sampling_backend.py",
        "test_radix_attention.py",
        "test_release_memory_occupation.py",
+        "test_request_length_validation.py",
        "test_retract_decode.py",
        "test_server_args.py",
        "test_session_control.py",