]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
model : add Kimi-K2 support (#14654)
authorGabriel Larson <redacted>
Tue, 15 Jul 2025 19:54:22 +0000 (14:54 -0500)
committerGitHub <redacted>
Tue, 15 Jul 2025 19:54:22 +0000 (21:54 +0200)
commit4a4f426944e79b79e389f9ed7b34831cb9b637ad
treedf9c5d189ab808cc1f720e4cff1aec79e6622a16
parentba1ceb34566c889a1fc500efa79799ffed25d9b0
model : add Kimi-K2 support (#14654)

* Kimi-K2 conversion

* add Kimi_K2  pre type

* Kimi-K2

* Kimi-K2 unicode

* Kimi-K2

* LLAMA_MAX_EXPERTS 384

* fix vocab iteration

* regex space fix

* add kimi-k2 to pre_computed_hashes

* Updated with kimi-k2 get_vocab_base_pre hash

* fix whitespaces

* fix flake errors

* remove more unicode.cpp whitespaces

* change set_vocab() flow

* add moonshotai-Kimi-K2.jinja to /models/templates/

* update moonshotai-Kimi-K2.jinja

* add kimi-k2 chat template

* add kimi-k2

* update NotImplementedError

Co-authored-by: Sigbjørn Skjæret <redacted>
* except Exception

Co-authored-by: Sigbjørn Skjæret <redacted>
* LLM_CHAT_TEMPLATE_KIMI_K2 if(add_ass){}

---------

Co-authored-by: Sigbjørn Skjæret <redacted>
convert_hf_to_gguf.py
convert_hf_to_gguf_update.py
models/templates/moonshotai-Kimi-K2.jinja [new file with mode: 0644]
src/llama-chat.cpp
src/llama-chat.h
src/llama-hparams.h
src/llama-vocab.cpp
src/llama-vocab.h
src/unicode.cpp
src/unicode.h