EngineX/xc-llm-ascend
3
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

[Refactor] [SP]The sequence parallelism characteristics in the MoE and Dense models are integrated into a single solution. (#3085)

Browse Source 
What this PR does / why we need it?

there are two sets of sp implementations for moe and dense models. One
is called sequence_parallelism, and the other is flashcomm_v1.
We did the following things：

Merge two sets of code with the same implementation into one.
Remove the implementation of sequence_parallelism, as this solution
cannot support aclgraph.
Does this PR introduce any user-facing change?

No

How was this patch tested?

e2e&ut

- vLLM version: v0.10.2
- vLLM main:
f225ea7dd9

---------

Signed-off-by: weijinqian_v1 <weijinqian@huawei.com>
Co-authored-by: weijinqian_v1 <weijinqian@huawei.com>
This commit is contained in:
weijinqian0
2025-09-24 11:29:59 +08:00
committed by GitHub
parent e7618d9414
commit 6aa4253798
14 changed files with 90 additions and 215 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
vllm_ascend/torchair/ops/torchair_fused_moe.py
View File

@@ -44,8 +44,8 @@ from vllm_ascend.distributed.parallel_state import get_mc2_group
from vllm_ascend.eplb.core.eplb_utils import (determine_default_expert_map,
determine_default_log2phy_map)
from vllm_ascend.ops.expert_load_balancer import ExpertLoadBalancer
from vllm_ascend.ops.sequence_parallel import MetadataForPadding
from vllm_ascend.quantization.quant_config import AscendFusedMoEMethod
from vllm_ascend.torchair.ops.sequence_parallel import MetadataForPadding
from vllm_ascend.torchair.utils import npu_stream_switch, npu_wait_tensor
from vllm_ascend.utils import (AscendSocVersion, dispose_tensor,
get_all_reduce_merge_state,