some fixes

Signed-off-by: MengqingCao <cmq0113@163.com>

Author: MengqingCao

docs/source/user_guide/additional_config.md

@@ -53,7 +53,7 @@ The details of each config option are as follows:
 | ---- | ---- | ------- | ----------- |
 | `enabled` | bool | `False` | Whether to enable ascend scheduler for V1 engine|
 
-ascend_scheduler_config also support the options from [vllm scheduler config](https://docs.vllm.ai/en/stable/api/vllm/config.html#vllm.config.SchedulerConfig). For example, you  can add `chunked_prefill_enabled: true` to ascend_scheduler_config as well.
+ascend_scheduler_config also support the options from [vllm scheduler config](https://docs.vllm.ai/en/stable/api/vllm/config.html#vllm.config.SchedulerConfig). For example, you  can add `enable_chunked_prefill: true` to ascend_scheduler_config as well.
 
 ### Example
 
@@ -62,18 +62,18 @@ A full example of additional configuration is as follows:
 ```
 {
     "torchair_graph_config": {
-        "enabled": true,
-        "use_cached_graph": true,
+        "enabled": True,
+        "use_cached_graph": True,
         "graph_batch_sizes": [1, 2, 4, 8],
-        "graph_batch_sizes_init": false,
-        "enable_multistream_moe": false,
-        "enable_kv_nz": false
+        "graph_batch_sizes_init": False,
+        "enable_multistream_moe": False,
+        "enable_kv_nz": False
     },
     "ascend_scheduler_config": {
-        "enabled": true,
-        "chunked_prefill_enabled": true,
+        "enabled": True,
+        "enable_chunked_prefill": True,
     },
     "expert_tensor_parallel_size": 1,
-    "refresh": false,
+    "refresh": False,
 }
 ```

docs/source/user_guide/graph_mode.md

@@ -47,14 +47,15 @@ from vllm import LLM
 
 os.environ["VLLM_USE_V1"] = 1
 
-model = LLM(model="deepseek-ai/DeepSeek-R1-0528", additional_config={"torchair_graph_config": {"enabled": True}})
+# TorchAirGraph is only work without chunked-prefill now
+model = LLM(model="deepseek-ai/DeepSeek-R1-0528", additional_config={"torchair_graph_config": {"enabled": True},"ascend_scheduler_config": {"enabled": True,}})
 outputs = model.generate("Hello, how are you?")
 ```
 
 online example:
 
 ```shell
-vllm serve Qwen/Qwen2-7B-Instruct --additional-config='{"torchair_graph_config": {"enabled": true}}'
+vllm serve Qwen/Qwen2-7B-Instruct --additional-config='{"torchair_graph_config": {"enabled": True},"ascend_scheduler_config": {"enabled": True,}}'
 ```
 
 You can find more detail about additional config [here](./additional_config.md)

tests/multicard/test_torchair_graph_mode.py

@@ -45,7 +45,7 @@ def test_e2e_deepseekv3_with_torchair(monkeypatch: pytest.MonkeyPatch):
         max_tokens = 5
         # torchair is only work without chunked-prefill now
         with VllmRunner(
-                "vllm-ascend/DeepSeek-V3",
+                "vllm-ascend/DeepSeek-V3-Pruning",
                 dtype=dtype,
                 tensor_parallel_size=4,
                 distributed_executor_backend="mp",
@@ -58,7 +58,6 @@ def test_e2e_deepseekv3_with_torchair(monkeypatch: pytest.MonkeyPatch):
                     },
                     "refresh": True,
                 },
-                load_format="dummy",
                 enforce_eager=False,
         ) as vllm_model:
             vllm_output = vllm_model.generate_greedy(example_prompts,