[Qwen3-next] Add PD disaggregation support for mamba with extra_buffer (#15180)

Signed-off-by: Shangming Cai <csmthu@gmail.com> Co-authored-by: ybyang <10629930+whybeyoung@users.noreply.github.com>
2025-12-16 14:36:00 +08:00
parent 6292d97135
commit 36fcf71fff
5 changed files with 79 additions and 7 deletions
@@ -157,7 +157,7 @@ suites = {
    "per-commit-8-gpu-h200": [
        TestFile("test_deepseek_v3_basic.py", 275),
        TestFile("test_deepseek_v3_mtp.py", 275),
-        TestFile("test_disaggregation_hybrid_attention.py", 200),
+        TestFile("test_disaggregation_hybrid_attention.py", 600),
        TestFile("models/test_kimi_k2_models.py", 200),
        TestFile("test_deepseek_v32_basic.py", 275),
        TestFile("test_deepseek_v32_mtp.py", 275),