Optimize MHC pipeline: DeepGemm, fused norm, fused hc_head (#24775)

Co-authored-by: Cheng Wan <chwan@rice.edu> Co-authored-by: Chunan Zeng <zcnrex@gmail.com>
2026-05-10 19:03:37 +08:00
parent bd0aa22309
commit 2f06867128
4 changed files with 513 additions and 74 deletions
@@ -424,6 +424,8 @@ def handle_rerun_stage(
        "stage-c-test-8-gpu-h20",
        "stage-c-test-4-gpu-b200",
        "stage-c-test-4-gpu-gb200",
+        "stage-c-test-dsv4-4-gpu-b200",
+        "stage-c-test-dsv4-8-gpu-h200",
        "stage-c-test-deepep-4-gpu-h100",
        "stage-c-test-deepep-8-gpu-h200",
        "stage-c-test-dsv4-4-gpu-b200",