Enable native ModelOpt quantization support (3/3) (#10154)

Signed-off-by: Zhiyu Cheng <zhiyuc@nvidia.com>
2025-10-21 21:44:29 -07:00
parent 4b65ed42cc
commit 80b2b3207a
16 changed files with 1528 additions and 39 deletions
--- a/test/srt/run_suite.py
+++ b/test/srt/run_suite.py
@@ -135,6 +135,8 @@ suites = {
        TestFile("test_vision_chunked_prefill.py", 175),
        TestFile("test_vision_openai_server_a.py", 918),
        TestFile("test_vlm_input_format.py", 300),
+        TestFile("test_modelopt_loader.py", 30),
+        TestFile("test_modelopt_export.py", 30),
    ],
    "per-commit-2-gpu": [
        TestFile("ep/test_moe_ep.py", 140),