revision based on review comments

Author: tardis-key

docs/ascend_tutorial/ascend_profiling_en.rst

@@ -1,4 +1,4 @@
-Data collection based on FSDP or MindSpeed(Megatron) on Ascend devices(en)
+Performance data collection based on FSDP or MindSpeed(Megatron) on Ascend devices(en)
 ==========================================================================================
 
 Last updated: 08/14/2025.

docs/ascend_tutorial/ascend_profiling_zh.rst

@@ -1,7 +1,7 @@
-Data collection based on FSDP or MindSpeed(Megatron) on Ascend devices(zh)
+Performance data collection based on FSDP or MindSpeed(Megatron) on Ascend devices(zh)
 ====================================
 
-在昇腾设备上基于FSDP或MindSpeed(Megatron)后端进行数据采集
+在昇腾设备上基于FSDP或MindSpeed(Megatron)后端进行性能数据采集
 
 Last updated: 08/14/2025.
 

verl/workers/fsdp_workers.py

@@ -1506,7 +1506,7 @@ def compute_values(self, data: DataProto):
         return output
 
     @register(dispatch_mode=make_nd_compute_dataproto_dispatch_fn(mesh_name="critic"))
-    @DistProfiler.annotate(color="pink", role="update_critic")
+    @DistProfiler.annotate(color="pink", role="critic_update")
     def update_critic(self, data: DataProto):
         if self._is_offload_param:
             load_fsdp_model_to_gpu(self.critic_module)

verl/workers/megatron_workers.py

@@ -1224,7 +1224,7 @@ def compute_values(self, data: DataProto):
         return output
 
     @register(dispatch_mode=make_nd_compute_dataproto_dispatch_fn(mesh_name="critic"))
-    @DistProfiler.annotate(color="pink", role="update_critic")
+    @DistProfiler.annotate(color="pink", role="critic_update")
     def update_critic(self, data: DataProto):
         data = data.to(get_device_id())