]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
model : Plamo3 support (#17304)
authormomonga <redacted>
Sun, 28 Dec 2025 16:28:31 +0000 (01:28 +0900)
committerGitHub <redacted>
Sun, 28 Dec 2025 16:28:31 +0000 (17:28 +0100)
commit9c675c714020748b5c3954ff334a946e29075f88
treed63c9b88e432a25738d96806203c7b65342dee12
parent07a0c4ba923a8caea3eeba060d399a28c461deac
model : Plamo3 support (#17304)

* plamo3

* fix plamo3

* clean code

* clean up the code

* fix diff

* clean up the code

* clean up the code

* clean up the code

* clean up the code

* clean up the code

* clean up the code

* add chat_template if exist

* clean up the code

* fix cpu-backend

* chore: whitespace trim fix + typo fix

* Fix: address review feedback

* restore `FREQ_BASE_SWA` constant

* Fix: address review feedback2

* Fix:typecheck

* Fix: address review feedback3

* final cleanup

---------

Co-authored-by: mmngays <redacted>
Co-authored-by: Sigbjørn Skjæret <redacted>
convert_hf_to_gguf.py
gguf-py/gguf/constants.py
gguf-py/gguf/tensor_mapping.py
src/CMakeLists.txt
src/llama-arch.cpp
src/llama-arch.h
src/llama-model.cpp
src/models/models.h
src/models/plamo3.cpp [new file with mode: 0644]