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

[bugfix]change log2phy map to npu (#3339)

Browse Source 
### What this PR does / why we need it?
Resolved the issue of EPLB failure caused by changes in the log2phy map
due to device type modifications when using MTP rotation position
encoding.

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

### How was this patch tested?
https://github.com/vllm-project/vllm/commit/releases/v0.11.0


- vLLM version: v0.11.0

---------

Signed-off-by: offline0806 <3337230449@qq.com>
Co-authored-by: offline0806 <3337230449@qq.com>
This commit is contained in:
offline893
2025-10-10 08:47:55 +08:00
committed by GitHub
parent 55e23fabec
commit 1c2c72af8d
3 changed files with 9 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

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

@@ -1045,7 +1045,7 @@ class TorchairAscendFusedMoE(FusedMoE):
self.global_redundant_expert_num)
self.log2phy = determine_default_log2phy_map(
self.global_num_experts, self.ep_size, self.ep_rank,
self.global_redundant_expert_num)
self.global_redundant_expert_num).npu()
local_num_experts = (torch.sum(self.expert_map != -1)
if self.expert_map is not None else num_experts)
if self.dynamic_eplb: