[Misc][Model][Refactor] Pass the prefix into Linear layers (#31669)

Signed-off-by: Wang Kunpeng <1289706727@qq.com>
This commit is contained in:
Wang Kunpeng
2026-01-05 20:03:18 +00:00
committed by GitHub
parent 02dbb933cb
commit 5708297e4e
17 changed files with 181 additions and 40 deletions
+1 -1
View File
@@ -166,7 +166,7 @@ class GPTNeoXLayer(nn.Module):
self.attention = GPTNeoXAttention(
config, cache_config, quant_config, prefix=f"{prefix}.attention"
)
self.mlp = GPTNeoXMLP(config, quant_config)
self.mlp = GPTNeoXMLP(config, quant_config, prefix=f"{prefix}.mlp")
def forward(
self,