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

[v0.11.0] [Bugfix] [MoE]fix error in deepseek when using allgather (#3827)

Browse Source 
### What this PR does / why we need it?
After refactoring vllm_ascend/models and FusedMoE, we are unable to pass
`gate` from deepseekv2.py to `AscendFusedMoE.forward`, which will result
in error when running deepseek v3/r1 with allgather.
Hence, this pr removes `gate` related computations from FusedMoE module
in eager/aclgraph mode.
### Does this PR introduce _any_ user-facing change?
`rm_router_logits` is deprecated in eager/aclgraph.
### How was this patch tested?
e2e & ut

Signed-off-by: Pr0Wh1teGivee <calvin_zhu0210@outlook.com>
This commit is contained in:
weichen
2025-10-30 14:59:46 +08:00
committed by GitHub
parent 211d4b9da4
commit c506ba60fb
7 changed files with 98 additions and 115 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
vllm_ascend/torchair/ops/torchair_fused_moe.py
View File

@@ -48,12 +48,12 @@ from vllm_ascend.eplb.core.eplb_utils import (determine_default_expert_map,
from vllm_ascend.ops.expert_load_balancer import ExpertLoadBalancer
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.torchair.utils import (get_all_reduce_merge_state,
get_rm_router_logits_state,
npu_stream_switch, npu_wait_tensor,
super_kernel)
from vllm_ascend.utils import (AscendSocVersion, dispose_tensor,
get_all_reduce_merge_state,
get_ascend_soc_version,
get_rm_router_logits_state, is_310p,
get_ascend_soc_version, is_310p,
is_hierarchical_communication_enabled)