kanshan/TensorRT-LLMs
1
0
Fork 0
mirror of https://github.com/NVIDIA/TensorRT-LLM.git synced 2026-01-14 06:27:45 +08:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity

Fix rotary_emb param in NemotronH attention (#3646)

Browse Source 
Signed-off-by: Luis Vega <vegaluisjose@users.noreply.github.com>
This commit is contained in:
Luis Vega 2025-04-16 21:03:07 -07:00 committed by GitHub
parent 950cadf2bd
commit a06bff5052
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 0 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
tensorrt_llm/_torch/models/modeling_nemotron_h.py
View File

@ -77,7 +77,6 @@ class TransformerLayer(Attention):
num_key_value_heads=config.num_key_value_heads,
max_position_embeddings=config.max_position_embeddings,
bias=config.attention_bias,
rotary_emb=None,
pos_embd_params=None,
layer_idx=layer_idx,
dtype=config.torch_dtype,