llama.cpp fork for Ternary Bonsai 2 27B: MTP speculation, suffix cache reuse (SCR), q8 KV, two-slot fairness, fused DeltaNet kernels
152 files

afmoe.cpp
apertus.cpp
arcee.cpp
arctic.cpp
arwkv7.cpp
baichuan.cpp
bailingmoe.cpp
bailingmoe2.cpp
bailingmoe3.cpp
bert.cpp
bitnet.cpp
bloom.cpp
chameleon.cpp
chatglm.cpp
clip.cpp
codeshell.cpp
cogvlm.cpp
cohere2.cpp
cohere2moe.cpp
command-r.cpp
dbrx.cpp
deci.cpp
deepseek.cpp
deepseek2.cpp
deepseek2ocr.cpp
deepseek32.cpp
deepseek4.cpp
delta-net-base.cpp
dflash.cpp
dots1.cpp
dots3note.cpp
dream.cpp
dspark.cpp
eagle3.cpp
ernie4-5-moe.cpp
ernie4-5.cpp
eurobert.cpp
exaone-moe.cpp
exaone.cpp
exaone4.cpp
falcon-h1.cpp
falcon.cpp
gemma-embedding.cpp
gemma.cpp
gemma2.cpp
gemma3.cpp
gemma3n.cpp
gemma4-assistant.cpp
gemma4.cpp
glm-dsa.cpp
glm4-moe.cpp
glm4.cpp
gpt2.cpp
gptneox.cpp
granite-hybrid.cpp
granite-moe.cpp
granite-swa.cpp
granite-switch.cpp
granite.cpp
grok.cpp
grovemoe.cpp
hunyuan-dense.cpp
hunyuan-moe.cpp
hunyuan-vl.cpp
hy-v3.cpp
internlm2.cpp
jais.cpp
jais2.cpp
jamba.cpp
jina-bert-v2.cpp
jina-bert-v3.cpp
kimi-k3.cpp
kimi-linear.cpp
laguna.cpp
lfm2.cpp
lfm2moe.cpp
llada-moe.cpp
llada.cpp
llama-embed.cpp
llama.cpp
llama4.cpp
maincoder.cpp
mamba-base.cpp
mamba.cpp
mamba2.cpp
mellum.cpp
mimo2.cpp
minicpm.cpp
minicpm3.cpp
minimax-01.cpp
minimax-m2.cpp
minimax-m3.cpp
mistral3.cpp
mistral4.cpp
models.h
modern-bert.cpp
mpt.cpp
muse-glimmer.cpp
nanbeige.cpp
nemotron-h-moe.cpp
nemotron-h.cpp
nemotron.cpp
neo-bert.cpp
nomic-bert-moe.cpp
nomic-bert.cpp
olmo.cpp
olmo2.cpp
olmoe.cpp
openai-moe.cpp
openelm.cpp
orion.cpp
paddleocr.cpp
pangu-embed.cpp
phi2.cpp
phi3.cpp
phimoe.cpp
plamo.cpp
plamo2.cpp
plamo3.cpp
plm.cpp
pockettts.cpp
qwen.cpp
qwen2.cpp
qwen2moe.cpp
qwen2vl.cpp
qwen3.cpp
qwen35.cpp
qwen35moe.cpp
qwen3moe.cpp
qwen3next.cpp
qwen3tts.cpp
qwen3vl.cpp
qwen3vlmoe.cpp
refact.cpp
rnd1.cpp
rwkv6-base.cpp
rwkv6.cpp
rwkv6qwen2.cpp
rwkv7-base.cpp
rwkv7.cpp
seed-oss.cpp
smallthinker.cpp
smollm3.cpp
stablelm.cpp
starcoder.cpp
starcoder2.cpp
step35.cpp
t5.cpp
t5encoder.cpp
talkie.cpp
wavtokenizer-dec.cpp
xverse.cpp