kanshan/TensorRT-LLMs
1
0
Fork 0
mirror of https://github.com/NVIDIA/TensorRT-LLM.git synced 2026-02-04 18:21:52 +08:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity

[None][feat] Nemotron H: Eagle3 support (#11131)

Browse Source 
Signed-off-by: Izzy Putterman <iputterman@nvidia.com>
This commit is contained in:
Izzy Putterman 2026-02-02 07:26:25 -08:00 committed by GitHub
parent cd7762a2fa
commit 3ef8a4639b
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 4 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
tensorrt_llm/_torch/models/modeling_nemotron_h.py
View File

@ -361,6 +361,10 @@ class NemotronHLayer(DecoderLayer):
spec_metadata=spec_metadata,
**kwargs)
hidden_states = torch.add(hidden_states, residual)
if spec_metadata is not None and spec_metadata.is_layer_capture(
self.layer_idx):
spec_metadata.maybe_capture_hidden_states(self.layer_idx,
hidden_states, None)
return hidden_states