merge main

Author: shihaobai

docs/CN/source/lightllm/lightllm_impl.rst

@@ -68,7 +68,7 @@ Model Backend
 * ``decode_batch`` : 对一个批次数据进行 ``decode``。
 
 每个backend都有一个 ``model``代表一个独立的模型类, 以及一个 ``tp_rank`` 代表一个设备，可以有若干个 ``backend``。
-其中的 ``model`` 类负责模型在设备中真正地计算， ``lightllm\common\basemodel\basemodel.py`` 中的 ``TpPartBaseModel`` 是所有模型类的基类，该类支持张量并行。
+其中的 ``model`` 类负责模型在设备中真正地计算， ``lightllm\common\basemodel\basemodel.py`` 中的 ``BaseModelRunner`` 是所有模型类的基类，该类支持张量并行。
 
 .. tip::
 

docs/CN/source/models/add_new_model.md

@@ -83,10 +83,10 @@ infer_struct.py 中的 InferStateInfo 类是进行一次模型推理时，在层
 
 ### 模型框架类
 
-basemodel.py 中的 TpPartBaseModel 类，是整个模型的入口，每个类型的模型都需要继承实现该类。该类通过类似搭积木的方式，使用推理类，权重类，状态类完成模型的加载，推理功能，其中有很多接口可以被继承实现，以完成每个模型类型自己独特的操作。
+basemodel.py 中的 BaseModelRunner 类，是整个模型的入口，每个类型的模型都需要继承实现该类。该类通过类似搭积木的方式，使用推理类，权重类，状态类完成模型的加载，推理功能，其中有很多接口可以被继承实现，以完成每个模型类型自己独特的操作。
 
 ~~~python
-class TpPartBaseModel:
+class BaseModelRunner:
     # weight class
     pre_and_post_weight_class = None
     transformer_weight_class = None
@@ -558,11 +558,11 @@ from lightllm.models.bloom.layer_infer.post_layer_infer import BloomPostLayerInf
 from lightllm.models.bloom.layer_infer.transformer_layer_infer import BloomTransformerLayerInfer
 from lightllm.models.bloom.layer_weights.pre_and_post_layer_weight import BloomPreAndPostLayerWeight
 from lightllm.models.bloom.layer_weights.transformer_layer_weight import BloomTransformerLayerWeight
-from lightllm.common.basemodel import InferStateInfo, TpPartBaseModel
+from lightllm.common.basemodel import InferStateInfo, BaseModelRunner
 
 from lightllm.common.build_utils import repair_config
 
-class BloomTpPartModel(TpPartBaseModel):
+class BloomTpPartModel(BaseModelRunner):
     # weight class
     pre_and_post_weight_class = BloomPreAndPostLayerWeight
     transformer_weight_class = BloomTransformerLayerWeight

docs/EN/source/lightllm/lightllm_impl.rst

@@ -67,7 +67,7 @@ After the ``Router`` decides which requests to use for ``prefill`` or ``decode``
 * ``prefill_batch``: Performs ``prefill`` on a batch of data.
 * ``decode_batch``: Performs ``decode`` on a batch of data.
 
-Each backend has a ``model`` that represents an independent model class, and a ``tp_rank`` that represents a device. There can be several ``backends``. The ``model`` class is responsible for the actual computation on the device, and the ``TpPartBaseModel`` in ``lightllm\common\basemodel\basemodel.py`` is the base class for all model classes, supporting tensor parallelism.
+Each backend has a ``model`` that represents an independent model class, and a ``tp_rank`` that represents a device. There can be several ``backends``. The ``model`` class is responsible for the actual computation on the device, and the ``BaseModelRunner`` in ``lightllm\common\basemodel\basemodel.py`` is the base class for all model classes, supporting tensor parallelism.
 
 .. tip::
 

docs/EN/source/models/add_new_model.md

@@ -83,10 +83,10 @@ The InferStateInfo class in infer_struct.py is a state class that passes some im
 
 ### Model class
 
-The TpPartBaseModel class in basemodel.py is the entry point of the entire model. Each type of model needs to inherit and implement this class. This class uses the inference class, weight class, and state class to complete the model loading and inference functions in a similar way to building blocks. Many of its interfaces can be inherited and implemented to complete the unique operations of each model type.
+The BaseModelRunner class in basemodel.py is the entry point of the entire model. Each type of model needs to inherit and implement this class. This class uses the inference class, weight class, and state class to complete the model loading and inference functions in a similar way to building blocks. Many of its interfaces can be inherited and implemented to complete the unique operations of each model type.
 
 ~~~python
-class TpPartBaseModel:
+class BaseModelRunner:
     # weight class
     pre_and_post_weight_class = None
     transformer_weight_class = None
@@ -560,11 +560,11 @@ from lightllm.models.bloom.layer_infer.post_layer_infer import BloomPostLayerInf
 from lightllm.models.bloom.layer_infer.transformer_layer_infer import BloomTransformerLayerInfer
 from lightllm.models.bloom.layer_weights.pre_and_post_layer_weight import BloomPreAndPostLayerWeight
 from lightllm.models.bloom.layer_weights.transformer_layer_weight import BloomTransformerLayerWeight
-from lightllm.common.basemodel import InferStateInfo, TpPartBaseModel
+from lightllm.common.basemodel import InferStateInfo, BaseModelRunner
 
 from lightllm.common.build_utils import repair_config
 
-class BloomTpPartModel(TpPartBaseModel):
+class BloomTpPartModel(BaseModelRunner):
     # weight class
     pre_and_post_weight_class = BloomPreAndPostLayerWeight
     transformer_weight_class = BloomTransformerLayerWeight