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

[CI][Bugfix] Quickfix for DPMetaData (#3234)

Browse Source 
### What this PR does / why we need it?
Fix `dpmetadata` and `Qwen3MoeSparseMoeBlock` break introduced by
26a7a33b88 (diff-c1550d0a38469d039370567d8981969530cbfffc7302cd1778e7c2c8a9322dea)

NOTE: we maintain a different sp in vllm-ascend with vllm, thus we can
just use `cu_tokens_across_sp(1)` as `cu_tokens_across_dp_cpu`

close https://github.com/vllm-project/vllm-ascend/issues/3236,
https://github.com/vllm-project/vllm-ascend/issues/3239
### Does this PR introduce _any_ user-facing change?

### How was this patch tested?


- vLLM version: v0.10.2
- vLLM main:
https://github.com/vllm-project/vllm/commit/releases/v0.11.0

---------

Signed-off-by: MengqingCao <cmq0113@163.com>
This commit is contained in:
Mengqing Cao
2025-09-28 21:11:22 +08:00
committed by GitHub
parent f2d8493221
commit 4ff422c730
7 changed files with 59 additions and 23 deletions
Download Patch File Download Diff File Expand all files Collapse all files

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

@@ -1242,8 +1242,12 @@ class TorchairAscendFusedMoE(FusedMoE):
router_logits = get_dp_group().all_gather(router_logits, 0)
elif fused_moe_state == FusedMoEState.NaiveMulticast:
cu_tokens_across_dp_cpu = get_forward_context(
).dp_metadata.cu_tokens_across_dp_cpu
if vllm_version_is("0.10.2"):
cu_tokens_across_dp_cpu = get_forward_context(
).dp_metadata.cu_tokens_across_dp_cpu
else:
cu_tokens_across_dp_cpu = get_forward_context(
).dp_metadata.cu_tokens_across_sp(1)
hidden_states = self.naive_multicast(hidden_states,
cu_tokens_across_dp_cpu)
if self.rm_router_logits: