[V1][Spec Decode] EAGLE-3 Support (#16937)

Signed-off-by: Bryan Lu <yuzhelu@amazon.com>
Signed-off-by: Benjamin Chislett <benjamin.chislett@centml.ai>
Co-authored-by: Bryan Lu <yuzhelu@amazon.com>
This commit is contained in:
Benjamin Chislett
2025-04-25 18:43:07 -04:00
committed by GitHub
parent 70116459c3
commit a0e619e62a
12 changed files with 358 additions and 34 deletions

View File

@@ -82,7 +82,8 @@ class LlamaModel(nn.Module):
hidden_states,
residual,
)
return hidden_states + residual
hidden_states = hidden_states + residual
return hidden_states, hidden_states
def load_weights(self, weights: Iterable[Tuple[str,
torch.Tensor]]) -> Set[str]: