Enable native ModelOpt quantization support (1/3) (#7149)

Signed-off-by: Zhiyu Cheng <zhiyuc@nvidia.com>
2025-10-06 13:24:15 -07:00
parent eb30b888db
commit 155cbb51f0
11 changed files with 464 additions and 42 deletions
--- a/test/srt/run_suite.py
+++ b/test/srt/run_suite.py
@@ -125,6 +125,7 @@ suites = {
        TestFile("test_vlm_input_format.py", 300),
        TestFile("test_vision_openai_server_a.py", 724),
        TestFile("test_vision_openai_server_b.py", 446),
+        TestFile("test_modelopt_loader.py", 30),
    ],
    "per-commit-2-gpu": [
        TestFile("lora/test_lora_tp.py", 116),