vlm: enable radix cache for qwen-vl models (#5349)

Co-authored-by: Xinyuan Tong <justinning0323@outlook.com>
2025-04-24 12:35:05 +09:00
parent 7d0edf3cae
commit c998d04b46
26 changed files with 429 additions and 331 deletions
--- a/test/srt/run_suite.py
+++ b/test/srt/run_suite.py
@@ -45,7 +45,7 @@ suites = {
        TestFile("test_mla_fp8.py", 93),
        TestFile("test_no_chunked_prefill.py", 126),
        TestFile("test_no_overlap_scheduler.py", 262),
-        TestFile("test_openai_server.py", 124),
+        TestFile("test_openai_server.py", 186),
        TestFile("test_penalty.py", 41),
        TestFile("test_page_size.py", 60),
        TestFile("test_pytorch_sampling_backend.py", 66),