mirror of
https://github.com/PaddlePaddle/FastDeploy.git
synced 2026-04-24 01:29:57 +08:00
[Optimization] merge matmul and add (#6986)
* merge matmul and add * modify format * using paddle.nn.functional.linear * using _C_ops.linear * using paddle.nn.functional.linear * add FLAGS_use_legacy_linear env var in test case * fix format * add assert and remove env * modify format * using matmul for no bias * modify accurate baseline
This commit is contained in:
@@ -157,10 +157,10 @@ def check_routing_replay_chat_completion(openai_client, moe_layer_num: int, mode
|
||||
model_path = os.getenv("MODEL_PATH")
|
||||
if model_path:
|
||||
baseline_path = os.path.join(
|
||||
model_path, f"R3_BaseLine_dev_uint8_0402/routing_replay_output_baseline_{model_name}"
|
||||
model_path, f"R3_BaseLine_dev_uint8_0403/routing_replay_output_baseline_{model_name}"
|
||||
)
|
||||
else:
|
||||
baseline_path = f"./R3_BaseLine_dev_uint8_0402/routing_replay_output_baseline_{model_name}"
|
||||
baseline_path = f"./R3_BaseLine_dev_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")
|
||||
|
||||
Reference in New Issue
Block a user