[model] Add mamba2 and Falcon-H1 support. (#10988)

Co-authored-by: Younes Belkada <younes.belkada@tii.ae> Co-authored-by: Younes B <49240599+younesbelkada@users.noreply.github.com>
2025-10-02 15:15:36 +04:00
parent b658be6f6a
commit 083629c235
18 changed files with 4533 additions and 1 deletions
--- a/test/srt/run_suite.py
+++ b/test/srt/run_suite.py
@@ -140,6 +140,7 @@ suites = {
        TestFile("test_local_attn.py", 250),
        TestFile("test_pp_single_node.py", 372),
        TestFile("models/test_qwen3_next_models.py", 200),
+        TestFile("models/test_falcon_h1_models.py", 200),
        TestFile("test_multi_instance_release_memory_occupation.py", 64),
    ],
    "per-commit-8-gpu": [