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

[main][bugfix] Modify the default value of the enable_shared_pert_dp to false (#2457)

Browse Source 
### What this PR does / why we need it?
enable_shared_pert_dp is currently on by default. This optimization is
currently only valid for deepseek series models. The default opening
affects the accuracy of the qwen series models.
### Does this PR introduce _any_ user-facing change?

### How was this patch tested?
use parameter --additional_config='{"enable_shared_expert_dp": true}'

- vLLM version: v0.10.0
- vLLM main:
d983769c41

Signed-off-by: Wang Kunpeng <1289706727@qq.com>
This commit is contained in:
Wang Kunpeng
2025-08-20 20:25:53 +08:00
committed by GitHub
parent c40d4171bc
commit 1de16ead8e
2 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
vllm_ascend/ascend_config.py
View File

@@ -48,7 +48,7 @@ class AscendConfig:
self.chunked_prefill_for_mla = additional_config.get(
"chunked_prefill_for_mla", False)
self.enable_shared_expert_dp = additional_config.get(
"enable_shared_expert_dp", True
"enable_shared_expert_dp", False
) and not self.torchair_graph_config.enabled and vllm_config.parallel_config.enable_expert_parallel