[Bugfix] Add constraints for sequence parallelism (#4014)

### What this PR does / why we need it?
Add Add constraints for sequence parallelism for unsupported scenarios:
1. tp_size > 1
2. enable_expert_parallel must be True for MoE model

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

### How was this patch tested?


- vLLM version: v0.11.0
- vLLM main:
83f478bb19

---------

Signed-off-by: realliujiaxu <realliujiaxu@163.com>
This commit is contained in:
realliujiaxu
2025-11-06 20:02:03 +08:00
committed by GitHub
parent 259eb25f88
commit 22005c64c1
2 changed files with 12 additions and 3 deletions

View File

@@ -115,12 +115,10 @@ def set_ascend_forward_context(
# the performance may degrade due to the switching of communication methods.
mmrs_fusion = True
if is_moe_model(vllm_config):
sp_enabled = enable_sp(vllm_config) and \
tp_world_size > 1 and num_tokens is not None
sp_enabled = enable_sp(vllm_config) and num_tokens is not None
mmrs_fusion = False
else:
sp_enabled = enable_sp(vllm_config) and \
tp_world_size > 1 and \
num_tokens is not None and num_tokens > 1000
forward_context.mmrs_fusion = mmrs_fusion