git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit

]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit

overview / pkg / ggml / sources / llama.cpp / commit

author	Max Krasnyansky <redacted>
	Mon, 8 Jun 2026 20:48:52 +0000 (13:48 -0700)
committer	GitHub <redacted>
	Mon, 8 Jun 2026 20:48:52 +0000 (13:48 -0700)
commit	7d2b45b4f7b663cda74f23fbc3ce6dc3bd4f6545
tree	eff64d75169aea06940e29b3d32f29eb9d5033ec	tree
parent	42a0afd59431815585ef8daa3277f9206b235531	commit \| diff

mtp: support for gemma-4 E2B and E4B assistants (#24282)

* models: update converter to support smaller assistants

* models: add masked_embd tensors to gemma4-assist arch

* gemma-4: remove temp debug for conversion

* gemma-4-mtp: filter out masked_embedding tensors during conversion

Packaging of ggml-org/llama.cpp

RSS Atom

conversion/gemma.py		diff \| blob \| history
gguf-py/gguf/constants.py		diff \| blob \| history
gguf-py/gguf/tensor_mapping.py		diff \| blob \| history
src/llama-arch.cpp		diff \| blob \| history
src/llama-arch.h		diff \| blob \| history
src/models/gemma4-assistant.cpp		diff \| blob \| history