[CI]Add EPLB CI. (#3568)

### What this PR does / why we need it?
1.Add eplb ci to check the change of eplb feature.
2.Add param checking of eplb params. 
### Does this PR introduce _any_ user-facing change?

### How was this patch tested?
Qwen in A3.


- vLLM version: v0.11.0rc3
- vLLM main: https://github.com/vllm-project/vllm/commit/v0.11.0

---------

Signed-off-by: offline0806 <3337230449@qq.com>
Co-authored-by: offline0806 <3337230449@qq.com>

vllm_ascend/eplb/core/eplb_utils.py

@@ -15,7 +15,9 @@
 # This file is a part of the vllm-ascend project.
 #
 # Todo: Once https://github.com/vllm-project/vllm/issues/22246 is merged in vllm. Remove eplb utils.
+import os.path
 import random
+import sys
 
 import torch
 from vllm.logger import logger
@@ -117,3 +119,72 @@ def determine_default_log2phy_map(global_expert_num, world_size, rank_id,
     log2phy_map_all = generate_log2phy_map(expert_map_all)
 
     return log2phy_map_all[rank_id]
+
+
+class EPLBParamUtils:
+
+    @staticmethod
+    def check_iterations(iterations):
+        if not isinstance(iterations, int):
+            raise TypeError(f"The {iterations} is not int.")
+        if iterations <= 0:
+            raise ValueError(
+                f"The {iterations} can not less than or equal to 0.")
+        if iterations > sys.maxsize:
+            raise ValueError(
+                f"The {iterations} can not large than {sys.maxsize}")
+
+    @staticmethod
+    def check_dynamic_eplb(dynamic_eplb):
+        if dynamic_eplb is None:
+            return
+        if not isinstance(dynamic_eplb, bool):
+            raise TypeError("The dynamic_eplb is not bool.")
+        if dynamic_eplb and os.getenv("DYNAMIC_EPLB", "false") != "true":
+            raise ValueError(
+                'Can not enable dynamic_eplb when not export DYNAMIC_EPLB="true".'
+            )
+
+    @staticmethod
+    def check_expert_map_path(expert_map):
+        if expert_map is None:
+            return
+        if not isinstance(expert_map, str):
+            raise TypeError("The expert_map is not str.")
+        if not expert_map.strip():
+            raise ValueError("The expert_map is not empty.")
+        _, ext = os.path.splitext(expert_map)
+        if ext.lower() != ".json":
+            raise TypeError("The expert_map is not json.")
+        if not os.path.exists(expert_map):
+            raise ValueError("The expert_map is not exist.")
+        try:
+            with open(expert_map, "w", encoding='utf-8') as f:
+                f.read()
+        except Exception as e:
+            raise IOError(
+                f"Fail read expert info from {expert_map}, please check the reading permission of {expert_map} : {e}"
+            )
+
+    @staticmethod
+    def check_expert_map_record_path(expert_map_record_path):
+        if expert_map_record_path is None:
+            return
+        if not isinstance(expert_map_record_path, str):
+            raise TypeError("The expert_map_record_path is not str.")
+        if not expert_map_record_path.strip():
+            raise ValueError("The expert_map_record_path is empty.")
+        _, ext = os.path.splitext(expert_map_record_path)
+        if ext.lower() != ".json":
+            raise TypeError("The expert_map_record_path is not json.")
+        if os.getenv("EXPERT_MAP_RECORD", "false") != "true":
+            raise ValueError(
+                'Can not enable expert_map_record_path when not export EXPERT_MAP_RECORD="true".'
+            )
+        try:
+            with open(expert_map_record_path, "w", encoding='utf-8') as f:
+                f.write("")
+        except Exception as e:
+            raise IOError(
+                f"Fail write expert info to {expert_map_record_path}, please check the writing permission of {expert_map_record_path} : {e}"
+            )

vllm_ascend/eplb/eplb_updator.py

@@ -21,6 +21,7 @@ import torch.distributed as dist
 import vllm.envs as envs
 from vllm.logger import logger
 
+from vllm_ascend.eplb.core.eplb_utils import EPLBParamUtils
 from vllm_ascend.eplb.core.eplb_worker import EplbProcess
 
 
@@ -44,6 +45,7 @@ class EplbUpdator:
         self.num_expert_load_gather = 10
         self.periodic_load_gather = True
         self.num_iterations_eplb_update: torch.int64 = self.ascend_config.num_iterations_eplb_update
+        EPLBParamUtils.check_iterations(self.num_iterations_eplb_update)
         self.expert_map_path = expert_map_path
         self.expert_map_record_path = self.ascend_config.expert_map_record_path
 
@@ -64,6 +66,7 @@ class EplbUpdator:
         self.cur_iterations: torch.int64 = 0
 
         self.num_wait_worker_iterations: torch.int64 = self.ascend_config.num_wait_worker_iterations
+        EPLBParamUtils.check_iterations(self.num_wait_worker_iterations)
 
         self.process = process
 

vllm_ascend/eplb/utils.py

@@ -71,7 +71,7 @@ def model_register(model, model_config):
     if config.model_type == "qwen3_moe":
         model.num_moe_layers = config.num_hidden_layers
     elif config.model_type == "deepseek_v2" or config.model_type == "deepseek_v3":
-        num_dense_layers = config.first_k_dense_replace
-        model.num_moe_layers = config.num_hidden_layers - num_dense_layers
+        model.num_dense_layers = config.first_k_dense_replace
+        model.num_moe_layers = config.num_hidden_layers - model.num_dense_layers
     else:
         raise NotImplementedError("EPLB is not supported.")