[EPLB]Eplb Config Renaming

docs/source/developer_guide/feature_guide/eplb_swift_balancer.md

@@ -179,7 +179,7 @@ class RandomLoadBalance(EplbPolicy):
 
 #### Integer Parameters
 
-All integer input parameters must explicitly specify their maximum and minimum values and be subject to valid value validation. For example, `num_iterations_eplb_update` must be greater than 0:
+All integer input parameters must explicitly specify their maximum and minimum values and be subject to valid value validation. For example, `expert_heat_collection_interval` must be greater than 0:
 
 ```python
     @staticmethod

docs/source/user_guide/configuration/additional_config.md

@@ -30,6 +30,7 @@ The following table lists additional configuration options available in vLLM Asc
 | `weight_prefetch_config`            | dict | `{}`    | Configuration options for weight prefetch                                                                 |
 | `finegrained_tp_config`             | dict | `{}`    | Configuration options for module tensor parallelism                                                       |
 | `ascend_compilation_config`         | dict | `{}`    | Configuration options for ascend compilation                                                              |
+| `eplb_config`                       | dict | `{}`    | Configuration options for ascend compilation |
 | `refresh`                           | bool | `false` | Whether to refresh global Ascend configuration content. This is usually used by rlhf or ut/e2e test case. |
 | `dump_config_path`                  | str  | `None`  | Configuration file path for msprobe dump(eager mode).                                                     |
 | `enable_async_exponential`          | bool | `False` | Whether to enable async exponential overlap. To enable async exponential, set this config to True.        |
@@ -41,13 +42,6 @@ The following table lists additional configuration options available in vLLM Asc
 | `SLO_limits_for_dynamic_batch`      | int  | `-1`    | SLO limits for dynamic batch. This is new scheduler to support dynamic feature                            |
 | `enable_npugraph_ex`                | bool | `False` | Whether to enable npugraph ex graph mode.                                                                 |
 | `pa_shape_list`                     | list | `[]`    | The custom shape list of page attention ops.                                                              |
-| `dynamic_eplb`                      | bool | `False` | Whether to enable dynamic EPLB.                                                                           |
-| `expert_map_path`                   | str  | `None`  | When using expert load balancing for an MoE model, an expert map path needs to be passed in.              |  
-| `num_iterations_eplb_update`        | int  | `400`   | Forward iterations when EPLB begins.                                                                      |
-| `gate_eplb`                         | bool | `False` | Whether to enable EPLB only once.                                                                         |
-| `num_wait_worker_iterations`        | int  | `30`    | The forward iterations when the EPLB worker will finish CPU tasks. In our test default value 30 can cover most cases. |
-| `expert_map_record_path`            | str  | `None`  | Save the expert load calculation results to a new expert table in the specified directory.                |
-| `init_redundancy_expert`            | int  | `0`     | Specify redundant experts during initialization.                                                          |
 | `enable_kv_nz`                      | bool | `False` | Whether to enable kvcache NZ layout. This option only takes effects on models using MLA (e.g., DeepSeek).                                      |
 | `layer_sharding` | dict | `{}` | Configuration options for layer sharding linear |
 
@@ -83,6 +77,17 @@ The details of each configuration option are as follows:
 | `fuse_norm_quant`  | bool | `True` | Whether to enable fuse_norm_quant pass. |
 | `fuse_qknorm_rope` | bool | `False` | Whether to enable fuse_qknorm_rope pass. It's set to True by default when Triton is installed. |
 
+**eplb_config**
+
+| Name | Type | Default | Description |
+| ---- | ---- | ------- | ----------- |
+| `dynamic_eplb`                   | bool| `False`| Whether to enable dynamic EPLB. |
+| `expert_map_path`                | str | `None` | When using expert load balancing for an MoE model, an expert map path needs to be passed in.|
+| `expert_heat_collection_interval`| int | `400`  | Forward iterations when EPLB begins. |
+| `algorithm_execution_interval`   | int | `30`   | The forward iterations when the EPLB worker will finish CPU tasks. |
+| `expert_map_record_path`         | str | `None` | Save the expert load calculation results to a new expert table in the specified directory.|
+| `num_redundant_experts`          | int | `0`    | Specify redundant experts during initialization. |
+
 ### Example
 
 An example of additional configuration is as follows:

docs/source/user_guide/feature_guide/eplb_swift_balancer.md

@@ -26,17 +26,17 @@ W8A8-dynamic
 
 ### Dynamic EPLB
 
-We need to add environment variable `export DYNAMIC_EPLB="true"` to enable vllm eplb. Enable dynamic balancing with auto-tuned parameters. Adjust num_iterations_eplb_update and num_wait_worker_iterations based on workload patterns.
+We need to add environment variable `export DYNAMIC_EPLB="true"` to enable vllm eplb. Enable dynamic balancing with auto-tuned parameters. Adjust expert_heat_collection_interval and algorithm_execution_interval based on workload patterns.
 
 ```shell
 vllm serve Qwen/Qwen3-235B-A22 \
   --tensor-parallel-size 16 \
   --enable-expert-parallel \
-  --additional-config '{
+  --additional-config '{ "eplb_config": {
     "dynamic_eplb": true,
-    "num_iterations_eplb_update": 400,
-    "num_wait_worker_iterations": 30
-  }'
+    "expert_heat_collection_interval": 400,
+    "algorithm_execution_interval": 30
+    }}'
 ```
 
 ### Static EPLB
@@ -49,12 +49,12 @@ We need to add environment variable `export EXPERT_MAP_RECORD="true"` to record
 vllm serve Qwen/Qwen3-235B-A22 \
   --tensor-parallel-size 16 \
   --enable-expert-parallel \
-  --additional-config '{
+  --additional-config '{ "eplb_config": {
     "expert_map_record_path": "/path/to/eplb.json",
-    "init_redundancy_expert": 16,
-    "num_iterations_eplb_update": 400,
-    "num_wait_worker_iterations": 30
-  }'
+    "num_redundant_experts": 16,
+    "expert_heat_collection_interval": 400,
+    "algorithm_execution_interval": 30
+  }}'
 ```
 
 #### Subsequent Deployments (Use Recorded Map)
@@ -73,9 +73,9 @@ vllm serve Qwen/Qwen3-235B-A22 \
 ## Critical Considerations
 
 1. Parameter Tuning:
-   - num_iterations_eplb_update: Higher values (e.g., 400+) for stable workloads; lower values (e.g., 100-200) for fluctuating traffic.
-   - num_wait_worker_iterations: Should be ≥ 30 to avoid premature balancing during startup.
-   - init_redundancy_expert: Must match tensor-parallel size (e.g., 16 for 16 GPUs) to ensure sufficient redundancy.
+   - expert_heat_collection_interval: Higher values (e.g., 400+) for stable workloads; lower values (e.g., 100-200) for fluctuating traffic.
+   - algorithm_execution_interval: Should be ≥ 30 to avoid premature balancing during startup.
+   - num_redundant_experts: Must match tensor-parallel size (e.g., 16 for 16 GPUs) to ensure sufficient redundancy.
 
 2. Hardware Requirements:
    - Ensure that all GPUs have identical memory capacity and compute capabilities.
@@ -85,20 +85,16 @@ vllm serve Qwen/Qwen3-235B-A22 \
    - Only MoE models with explicit expert parallelism support (e.g., Qwen3 MoE models) are compatible.
    - Verify model architecture supports dynamic expert routing through --enable-expert-parallel.
 
-4. Gating Configuration:
-   - When gate_eplb=true, validate that the gating mechanism can handle expert movement without routing errors.
-   - Test with synthetic workloads before production deployment.
-
-5. Monitoring & Validation:
+4. Monitoring & Validation:
    - Track metrics: expert_load_balance_ratio, ttft_p99, tpot_avg, and gpu_utilization.
    - Use vllm monitor to detect imbalances during runtime.
    - Always verify expert map JSON structure before loading (validate with jq or similar tools).
 
-6. Startup Behavior:
+5. Startup Behavior:
    - Initial requests may experience higher latency during the first balancing cycle (typically 1-2 minutes).
    - Avoid sudden traffic spikes during the warm-up phase.
 
-7. Common Pitfalls:
+6. Common Pitfalls:
    - Incorrect tensor-parallel-size vs. actual GPU count → causes resource underutilization.
    - Using expert_map_path without generating the map first → runtime errors.
-   - Setting init_redundancy_expert > available GPUs → system failure.
+   - Setting num_redundant_experts > available GPUs → system failure.

tests/e2e/multicard/2-cards/test_qwen3_moe.py

@@ -105,10 +105,12 @@ async def test_qwen3_moe_w8a8_distributed_tp2_ep_dynamic_eplb():
     # during initialization in offline mode, so the online mode is used instead.
     env_dict.update({"DYNAMIC_EPLB": "true"})
     additional_config = {
-        "dynamic_eplb": True,
-        "num_iterations_eplb_update": 100,
-        "num_wait_worker_iterations": 20,
-        "num_redundant_experts": 2
+        "eplb_config": {
+            "dynamic_eplb": True,
+            "expert_heat_collection_interval": 100,
+            "algorithm_execution_interval": 20,
+            "num_redundant_experts": 2
+        }
     }
     server_args.extend(["--additional-config", json.dumps(additional_config)])
     with RemoteOpenAIServer(model,

tests/e2e/nightly/multi_node/config/DeepSeek-R1-W8A8-EPLB.yaml

@@ -55,7 +55,7 @@ deployment:
               }
           }'
           --additional-config
-          '{"dynamic_eplb":true,"num_iterations_eplb_update":2048,"num_wait_worker_iterations":200}'
+          '{"enable_prefill_optimizations":true,"enable_weight_nz_layout":true,"eplb_config": {"dynamic_eplb":true,"expert_heat_collection_interval":2048,"algorithm_execution_interval":200}}'
 
   -
     server_cmd: >
@@ -92,7 +92,7 @@ deployment:
               }
           }'
           --additional-config
-          '{"dynamic_eplb":true,"num_iterations_eplb_update":2048,"num_wait_worker_iterations":200}'
+          '{"enable_prefill_optimizations":true,"enable_weight_nz_layout":true,"eplb_config": {"dynamic_eplb":true,"expert_heat_collection_interval":2048,"algorithm_execution_interval":200}}'
   -
     server_cmd: >
       vllm serve vllm-ascend/DeepSeek-R1-0528-W8A8
@@ -130,7 +130,7 @@ deployment:
             }
         }'
         --additional-config
-        '{"multistream_overlap_shared_expert":true,"dynamic_eplb":true,"num_iterations_eplb_update":2048,"num_wait_worker_iterations":200}'
+        '{"multistream_overlap_shared_expert":true,"dynamic_eplb":true,"expert_heat_collection_interval":2048,"algorithm_execution_interval":200}'
   -
     server_cmd: >
       vllm serve vllm-ascend/DeepSeek-R1-0528-W8A8
@@ -167,7 +167,7 @@ deployment:
             }
         }'
         --additional-config
-        '{"multistream_overlap_shared_expert":true,"dynamic_eplb":true,"num_iterations_eplb_update":2048,"num_wait_worker_iterations":200}'
+        '{"multistream_overlap_shared_expert":true,"eplb_config": {"dynamic_eplb":true,"expert_heat_collection_interval":2048,"algorithm_execution_interval":200}}'
 benchmarks:
   perf:
     case_type: performance

tests/e2e/nightly/multi_node/config/Qwen3-235B-W8A8-EPLB.yaml

@@ -51,7 +51,7 @@ deployment:
             }
         }'
         --additional-config
-        '{"dynamic_eplb":true,"num_iterations_eplb_update":2048,"num_wait_worker_iterations":200}'
+        '{"eplb_config": {"dynamic_eplb":true,"expert_heat_collection_interval":2048,"algorithm_execution_interval":200}}'
 
   -
     server_cmd: >
@@ -87,5 +87,5 @@ deployment:
             }
         }'
         --additional-config
-        '{"dynamic_eplb":true,"num_iterations_eplb_update":2048,"num_wait_worker_iterations":200}'
+        '{"eplb_config": {"dynamic_eplb":true,"expert_heat_collection_interval":2048,"algorithm_execution_interval":200}}'
 benchmarks:

tests/e2e/nightly/single_node/models/test_deepseek_r1_0528_w8a8_eplb.py

@@ -70,11 +70,12 @@ async def test_models(model: str) -> None:
     additional_config: dict[str, Any] = {
         "enable_shared_expert_dp": False,
         "multistream_overlap_shared_expert": False,
-        "dynamic_eplb": True,
-        "num_iterations_eplb_update": 14000,
-        "num_wait_worker_iterations": 30,
-        "init_redundancy_expert": 0,
-        "gate_eplb": False
+        "eplb_config": {
+            "dynamic_eplb": True,
+            "expert_heat_collection_interval": 512,
+            "algorithm_execution_interval": 100,
+            "num_redundant_experts": 0
+        }
     }
     server_args = [
         "--quantization", "ascend", "--seed", "1024",

tests/e2e/nightly/single_node/models/test_qwen3_235b_a22b_w8a8_eplb.py

@@ -70,13 +70,13 @@ async def test_models(model: str) -> None:
         "8192", "--max-num-seqs", "12", "--trust-remote-code",
         "--gpu-memory-utilization", "0.9"
     ]
-    env_dict["EXPERT_MAP_RECORD"] = "true"
     env_dict["DYNAMIC_EPLB"] = "true"
-    additional_config["dynamic_eplb"] = True
-    additional_config["num_iterations_eplb_update"] = 14000
-    additional_config["num_wait_worker_iterations"] = 30
-    additional_config["init_redundancy_expert"] = 0
-    additional_config["gate_eplb"] = False
+    additional_config["eplb_config"] = {
+        "dynamic_eplb": True,
+        "expert_heat_collection_interval": 512,
+        "algorithm_execution_interval": 100,
+        "num_redundant_experts": 0
+    }
     server_args.extend(
         ["--compilation-config",
          json.dumps(compilation_config)])