[Cherry-Pick][Optimization] merge matmul and add(#6986) (#7184)

* replace matmul+add to linear

* modify baseline

Author: BingooYang

fastdeploy/model_executor/layers/linear.py

@@ -82,10 +82,16 @@ def process_loaded_weights(self, layer, weights) -> None:
         layer.weight.set_value(weights)
 
     def apply(self, layer: nn.Layer, x: paddle.Tensor) -> paddle.Tensor:
-        linear_out = paddle.matmul(x, layer.weight)
         if layer.with_bias:
-            linear_out = paddle.add(linear_out, layer.bias)
-        return linear_out
+            bias = layer.bias
+            assert bias.dim() == 1 and bias.shape[-1] == layer.weight.shape[-1], (
+                f"bias must be 1D with size equal to the last dim of weight, "
+                f"but got bias.shape={bias.shape}, weight.shape[-1]={layer.weight.shape[-1]}"
+            )
+            out = paddle.nn.functional.linear(x, layer.weight, bias)
+        else:
+            out = paddle.matmul(x, layer.weight)
+        return out
 
 
 class LinearBase(nn.Layer):

tests/e2e/4cards_cases/test_GLM_45_AIR_mtp_tp4.py

@@ -184,7 +184,7 @@ def test_lm_head_fp32(api_url, headers, consistent_payload):
     # 校验返回内容与概率信息
     assert (
         resp_json["choices"][0]["message"]["content"]
-        == "\n<think>这个问题是关于牛顿的三大运动定律的。牛顿的三大运动定律是经典"
+        == "\n<think>我需要回答牛顿的三大运动定律是什么。牛顿的三大运动定律是经典"
     ), f"The response content is not as expected {resp_json['choices'][0]['message']['content']}."
 
 

tests/e2e/4cards_cases/test_GLM_45_AIR_tp4.py

@@ -181,7 +181,7 @@ def test_lm_head_fp32(api_url, headers, consistent_payload):
     # 校验返回内容与概率信息
     assert (
         resp_json["choices"][0]["message"]["content"]
-        == "\n<think>这个问题是关于牛顿的三大运动定律的。牛顿的三大运动定律是经典"
+        == "\n<think>我需要回答牛顿的三大运动定律是什么。牛顿的三大运动定律是经典"
     ), f"The response content is not as expected {resp_json['choices'][0]['message']['content']}."
 
 

tests/e2e/utils/rollout_routing_replay_test_utils.py

@@ -156,9 +156,11 @@ def check_routing_replay_chat_completion(openai_client, moe_layer_num: int, mode
     cur_save_routing_path = f"./R3_tmp/routing_replay_output_{model_name}/"
     model_path = os.getenv("MODEL_PATH")
     if model_path:
-        baseline_path = os.path.join(model_path, f"R3_BaseLine_25_uint8/routing_replay_output_baseline_{model_name}")
+        baseline_path = os.path.join(
+            model_path, f"R3_BaseLine_25_uint8_0403/routing_replay_output_baseline_{model_name}"
+        )
     else:
-        baseline_path = f"./R3_BaseLine_25_uint8/routing_replay_output_baseline_{model_name}"
+        baseline_path = f"./R3_BaseLine_25_uint8_0403/routing_replay_output_baseline_{model_name}"
     stream_baseline_path = os.path.join(baseline_path, "r3_chat_completion_stream")
 
     nonstream_baseline_path = os.path.join(baseline_path, "r3_chat_completion_nonstream")