PR #18058 llama : add support for NVIDIA Nemotron 3 Nano

llama : add support for NVIDIA Nemotron 3 Nano #18058

danbev merged 8 commits into ggml-org:master from danbev:nemotron-nano-3

llama : add support for NVIDIA Nemotron Nano 3

0aebd861

danbev requested a review from

CISC 31 days ago

ggerganov changed the title ~~llama : add support for NVIDIA Nemotron Nano 3~~ llama : add support for NVIDIA Nemotron 3 Nano 31 days ago

ggerganov commented on 2025-12-15

fix indentation in llama-graph.cpp

31240ce2

fix indentation and move ffn_inp

c257b1f1

convert : fix modify_tensors in NemotronHModel to call super()

436e2f02

fix pyright error

f0618945

jeffbolznv commented on 2025-12-15

ggerganov approved these changes on 2025-12-15

github-actions added model

github-actions added python

fix flake8 errors

1d4f2423

CISC approved these changes on 2025-12-15

llama : fix inconsistent brace style in switch [no ci]

64a8586c

gguf-py : make e_score_correction_bias tensor name consistent

9f66613f

danbev merged 29953417 into master 30 days ago

danbev deleted the nemotron-nano-3 branch 1 day ago

Reviewers

CISC

ggerganov

jeffbolznv

Assignees

No one assigned

Labels

model python

Milestone

No milestone