Skip to content

Conversation

@pull
Copy link

@pull pull bot commented Jan 26, 2026

See Commits and Changes for more details.


Created by pull[bot] (v2.0.0-alpha.4)

Can you help keep this open source service alive? 💖 Please sponsor : )

* fix(examples): te_llama compatibility with HuggingFace transformers >= 4.57

The te_llama.py example was failing with HuggingFace transformers 4.57+
due to API changes in how decoder layer outputs are handled.

Changes:
- Handle case where hidden_states is passed as a tuple (older HF versions)
- Return tensor directly instead of wrapped in tuple (HF 4.57+ expects this)
- Fix regex pattern to use raw string (fixes SyntaxWarning)

Error fixed:
  AttributeError: 'tuple' object has no attribute 'contiguous'

Tested with:
- transformer_engine 2.5.0
- transformers 4.57.3
- PyTorch container nvcr.io/nvidia/pytorch:25.08-py3

Signed-off-by: Santosh Bhavani <santosh.bhavani@live.com>

* docs(te_llama): add requirements.txt

Signed-off-by: Santosh Bhavani <santosh.bhavani@live.com>

* fix(docs): add missing notebook output names

Signed-off-by: Santosh Bhavani <santosh.bhavani@live.com>

---------

Signed-off-by: Santosh Bhavani <santosh.bhavani@live.com>
@pull pull bot locked and limited conversation to collaborators Jan 26, 2026
@pull pull bot added the ⤵️ pull label Jan 26, 2026
@pull pull bot merged commit 2dbfbc7 into phu0ngng:main Jan 26, 2026
Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant