diff --git a/docs/pytorch/features/cc_lora.md b/docs/pytorch/features/cc_lora.md
index dee22b812e1c2db35cead706a27784770ef85f46..e3a4ea2ed67782024025238c3a31855ab85040b0 100644
--- a/docs/pytorch/features/cc_lora.md
+++ b/docs/pytorch/features/cc_lora.md
@@ -40,6 +40,8 @@ RC2以上版本，LoRA微调场景，算法与PP、VPP、分布式优化器等
 
 通过设置--lora-fusion开启CCLoRA的加速，在开启了TP或SP场景，加入--use-fused-mlp启用[Fused_MLP](fused_mlp.md)算法，针对LoRA的MLP模块进一步进行计算通信掩盖提高性能。
 
+注意:cclora 与 --overlap-param-gather 特性冲突 , 不能同时使用 。
+
 ## 使用效果
 
 以下验证硬件信息为Atlas 900 A2 PODc，集群规模1x8
diff --git a/examples/mcore/qwen25/tune_qwen25_14b_4k_lora_ptd.sh b/examples/mcore/qwen25/tune_qwen25_14b_4k_lora_ptd.sh
index ce79321711eafe8191c40defa8136442ef822e7d..7afd8cd2339c940b555d76a542f2ab9e3e76cec2 100644
--- a/examples/mcore/qwen25/tune_qwen25_14b_4k_lora_ptd.sh
+++ b/examples/mcore/qwen25/tune_qwen25_14b_4k_lora_ptd.sh
@@ -51,7 +51,6 @@ GPT_ARGS="
     --reuse-fp32-param \
     --use-distributed-optimizer \
     --overlap-grad-reduce \
-    --overlap-param-gather \
     --hidden-size 5120 \
     --ffn-hidden-size 13824 \
     --num-attention-heads 40 \
diff --git a/examples/mcore/qwen25/tune_qwen25_32b_4k_lora_ptd.sh b/examples/mcore/qwen25/tune_qwen25_32b_4k_lora_ptd.sh
index dfe5272d49847156d854205a8de7db08a87096df..3757bee3dde98e15ff949b4660c19d37f00cea57 100644
--- a/examples/mcore/qwen25/tune_qwen25_32b_4k_lora_ptd.sh
+++ b/examples/mcore/qwen25/tune_qwen25_32b_4k_lora_ptd.sh
@@ -51,7 +51,6 @@ GPT_ARGS="
     --reuse-fp32-param \
     --use-distributed-optimizer \
     --overlap-grad-reduce \
-    --overlap-param-gather \
     --sequence-parallel \
     --hidden-size 5120  \
     --ffn-hidden-size 27648 \
diff --git a/examples/mcore/qwen25/tune_qwen25_7b_4k_lora_ptd.sh b/examples/mcore/qwen25/tune_qwen25_7b_4k_lora_ptd.sh
index e13868873dfb4f869f0a80711f5164df2e0c92bb..904098aa3c9b0a92cb8571453d7fb35e077c45e6 100644
--- a/examples/mcore/qwen25/tune_qwen25_7b_4k_lora_ptd.sh
+++ b/examples/mcore/qwen25/tune_qwen25_7b_4k_lora_ptd.sh
@@ -47,7 +47,6 @@ GPT_ARGS="
     --use-mcore-models \
     --use-distributed-optimizer \
     --overlap-grad-reduce \
-    --overlap-param-gather \
     --tensor-model-parallel-size ${TP} \
     --pipeline-model-parallel-size ${PP} \
     --num-layers 28 \