]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 1725e31)
mtmd : Add Nemotron Nano 12B v2 VL support (#19547)
authorAnav Prasad <redacted>
Sat, 14 Feb 2026 13:07:00 +0000 (05:07 -0800)
committerGitHub <redacted>
Sat, 14 Feb 2026 13:07:00 +0000 (14:07 +0100)
commit01d8eaa28d57bfc6d06e30072085ed0ef12e06c5
treed2d6f93a488b6ecbe9d1a876f200fdfbe67a9a7ftree
parent1725e316c1a780759ec134ca5a2999f4d53ce273commit | diff
mtmd : Add Nemotron Nano 12B v2 VL support (#19547)

* nemotron nano v2 vlm support added

* simplified code; addressed reviews

* pre-downsample position embeddings during GGUF conversion for fixed input size
convert_hf_to_gguf.py diff | blob | history
gguf-py/gguf/constants.py diff | blob | history
gguf-py/gguf/tensor_mapping.py diff | blob | history
tools/mtmd/CMakeLists.txt diff | blob | history
tools/mtmd/clip-impl.h diff | blob | history
tools/mtmd/clip-model.h diff | blob | history
tools/mtmd/clip.cpp diff | blob | history
tools/mtmd/models/models.h diff | blob | history
tools/mtmd/models/nemotron-v2-vl.cpp [new file with mode: 0644] blob
Packaging of ggml-org/llama.cpp