Revert "[Feat] enable hierarchical mc2 ops on A2 by default (#5545)" (#5611)

This reverts commit fb9fdcdbe4.

### What this PR does / why we need it?
this pr breaks the smoke test because of that leads the error of
aclnnNeScalar:Kernel Run failed. opType: 25, NotEqual
        launch failed for NotEqual, errno:361001
<img width="1149" height="166"
alt="A6C9453D-4F0B-4256-DD80-A9C181DAB2D9"
src="https://github.com/user-attachments/assets/cab9c4b8-3fd1-4c6b-b424-474b46042726"
/>

### Does this PR introduce _any_ user-facing change?

### How was this patch tested?

- vLLM version: v0.13.0
- vLLM main:
7157596103

Signed-off-by: zxwang <1476209578@qq.com>
This commit is contained in:
ZixuanWang
2026-01-05 22:39:05 +08:00
committed by GitHub
parent 11e75494b1
commit 8eae949d11
2 changed files with 20 additions and 10 deletions

View File

@@ -983,6 +983,14 @@ def calculate_dp_buffer_size() -> int:
return max(dp_buffer_size, _MIN_DP_BUFFER_SIZE)
# Currently, when in A2, setting the environment variables HCCL_INTRA_PCIE_ENABLE=1
# and HCCL_INTRA_ROCE_ENABLE=0 can reduce cross-machine communication traffic and
# significantly improve communication performance of MC2 ops dispatch/combine.
def is_hierarchical_communication_enabled():
return (os.getenv("HCCL_INTRA_ROCE_ENABLE", "") == "0"
and os.getenv("HCCL_INTRA_PCIE_ENABLE", "") == "1")
def has_layer_idx(model_instance: torch.nn.Module) -> bool:
if model_instance is None:
return False