mirror of
https://github.com/PaddlePaddle/FastDeploy.git
synced 2025-10-04 16:22:57 +08:00
[Sync] Update to latest code (#2679)
* [Sync] Update to latest code * Add new code files * Add new code files * update code * Try to fix build.sh * Try to fix build.sh * Update code * Update requirements.txt * Update code --------- Co-authored-by: Jiang-Jia-Jun <jiangjiajun@baidu.com>
This commit is contained in:
@@ -68,7 +68,7 @@ class Qwen3Attention(nn.Layer):
|
||||
fd_config=fd_config,
|
||||
prefix=f"{prefix}.o_proj",
|
||||
input_size=fd_config.model_config.head_dim *
|
||||
fd_config.model_config.num_attention_heads // nranks,
|
||||
fd_config.model_config.num_attention_heads,
|
||||
output_size=fd_config.model_config.hidden_size,
|
||||
)
|
||||
|
||||
|
Reference in New Issue
Block a user