ollama/llama/llama.cpp/src/models
Daniel Hiltgen 0cf7794b16
ggml update to b7108 (#12992)
* Revert "vulkan: temporary cary of vulkan fixes (#12971)"

This reverts commit 3a9e8e9fd4.

* ggml update to b7087

* fix argsort on metal

* update to b7108

* fix bakllava regression

This model lacks the metadata for the projector type.

* update to b7209

* fix TopK perf

* only build arm code on arm
2025-12-03 19:43:29 -08:00
..
afmoe.cpp ggml update to b7108 (#12992) 2025-12-03 19:43:29 -08:00
apertus.cpp ggml update to b7108 (#12992) 2025-12-03 19:43:29 -08:00
arcee.cpp ggml update to b7108 (#12992) 2025-12-03 19:43:29 -08:00
arctic.cpp ggml update to b7108 (#12992) 2025-12-03 19:43:29 -08:00
arwkv7.cpp ggml update to b7108 (#12992) 2025-12-03 19:43:29 -08:00
baichuan.cpp ggml update to b7108 (#12992) 2025-12-03 19:43:29 -08:00
bailingmoe.cpp ggml update to b7108 (#12992) 2025-12-03 19:43:29 -08:00
bailingmoe2.cpp ggml update to b7108 (#12992) 2025-12-03 19:43:29 -08:00
bert.cpp ggml update to b7108 (#12992) 2025-12-03 19:43:29 -08:00
bitnet.cpp ggml update to b7108 (#12992) 2025-12-03 19:43:29 -08:00
bloom.cpp ggml update to b7108 (#12992) 2025-12-03 19:43:29 -08:00
chameleon.cpp ggml update to b7108 (#12992) 2025-12-03 19:43:29 -08:00
chatglm.cpp ggml update to b7108 (#12992) 2025-12-03 19:43:29 -08:00
codeshell.cpp ggml update to b7108 (#12992) 2025-12-03 19:43:29 -08:00
cogvlm.cpp ggml update to b7108 (#12992) 2025-12-03 19:43:29 -08:00
cohere2-iswa.cpp ggml update to b7108 (#12992) 2025-12-03 19:43:29 -08:00
command-r.cpp ggml update to b7108 (#12992) 2025-12-03 19:43:29 -08:00
dbrx.cpp ggml update to b7108 (#12992) 2025-12-03 19:43:29 -08:00
deci.cpp ggml update to b7108 (#12992) 2025-12-03 19:43:29 -08:00
deepseek.cpp ggml update to b7108 (#12992) 2025-12-03 19:43:29 -08:00
deepseek2.cpp ggml update to b7108 (#12992) 2025-12-03 19:43:29 -08:00
dots1.cpp ggml update to b7108 (#12992) 2025-12-03 19:43:29 -08:00
dream.cpp ggml update to b7108 (#12992) 2025-12-03 19:43:29 -08:00
ernie4-5-moe.cpp ggml update to b7108 (#12992) 2025-12-03 19:43:29 -08:00
ernie4-5.cpp ggml update to b7108 (#12992) 2025-12-03 19:43:29 -08:00
exaone.cpp ggml update to b7108 (#12992) 2025-12-03 19:43:29 -08:00
exaone4.cpp ggml update to b7108 (#12992) 2025-12-03 19:43:29 -08:00
falcon-h1.cpp ggml update to b7108 (#12992) 2025-12-03 19:43:29 -08:00
falcon.cpp ggml update to b7108 (#12992) 2025-12-03 19:43:29 -08:00
gemma-embedding.cpp ggml update to b7108 (#12992) 2025-12-03 19:43:29 -08:00
gemma.cpp ggml update to b7108 (#12992) 2025-12-03 19:43:29 -08:00
gemma2-iswa.cpp ggml update to b7108 (#12992) 2025-12-03 19:43:29 -08:00
gemma3-iswa.cpp ggml update to b7108 (#12992) 2025-12-03 19:43:29 -08:00
gemma3n-iswa.cpp ggml update to b7108 (#12992) 2025-12-03 19:43:29 -08:00
glm4-moe.cpp ggml update to b7108 (#12992) 2025-12-03 19:43:29 -08:00
glm4.cpp ggml update to b7108 (#12992) 2025-12-03 19:43:29 -08:00
gpt2.cpp ggml update to b7108 (#12992) 2025-12-03 19:43:29 -08:00
gptneox.cpp ggml update to b7108 (#12992) 2025-12-03 19:43:29 -08:00
granite-hybrid.cpp ggml update to b7108 (#12992) 2025-12-03 19:43:29 -08:00
granite.cpp ggml update to b7108 (#12992) 2025-12-03 19:43:29 -08:00
graph-context-mamba.cpp ggml update to b7108 (#12992) 2025-12-03 19:43:29 -08:00
grok.cpp ggml update to b7108 (#12992) 2025-12-03 19:43:29 -08:00
grovemoe.cpp ggml update to b7108 (#12992) 2025-12-03 19:43:29 -08:00
hunyuan-dense.cpp ggml update to b7108 (#12992) 2025-12-03 19:43:29 -08:00
hunyuan-moe.cpp ggml update to b7108 (#12992) 2025-12-03 19:43:29 -08:00
internlm2.cpp ggml update to b7108 (#12992) 2025-12-03 19:43:29 -08:00
jais.cpp ggml update to b7108 (#12992) 2025-12-03 19:43:29 -08:00
jamba.cpp ggml update to b7108 (#12992) 2025-12-03 19:43:29 -08:00
lfm2.cpp ggml update to b7108 (#12992) 2025-12-03 19:43:29 -08:00
llada-moe.cpp ggml update to b7108 (#12992) 2025-12-03 19:43:29 -08:00
llada.cpp ggml update to b7108 (#12992) 2025-12-03 19:43:29 -08:00
llama-iswa.cpp ggml update to b7108 (#12992) 2025-12-03 19:43:29 -08:00
llama.cpp ggml update to b7108 (#12992) 2025-12-03 19:43:29 -08:00
mamba.cpp ggml update to b7108 (#12992) 2025-12-03 19:43:29 -08:00
minicpm3.cpp ggml update to b7108 (#12992) 2025-12-03 19:43:29 -08:00
minimax-m2.cpp ggml update to b7108 (#12992) 2025-12-03 19:43:29 -08:00
models.go ggml update to b7108 (#12992) 2025-12-03 19:43:29 -08:00
models.h ggml update to b7108 (#12992) 2025-12-03 19:43:29 -08:00
mpt.cpp ggml update to b7108 (#12992) 2025-12-03 19:43:29 -08:00
nemotron-h.cpp ggml update to b7108 (#12992) 2025-12-03 19:43:29 -08:00
nemotron.cpp ggml update to b7108 (#12992) 2025-12-03 19:43:29 -08:00
neo-bert.cpp ggml update to b7108 (#12992) 2025-12-03 19:43:29 -08:00
olmo.cpp ggml update to b7108 (#12992) 2025-12-03 19:43:29 -08:00
olmo2.cpp ggml update to b7108 (#12992) 2025-12-03 19:43:29 -08:00
olmoe.cpp ggml update to b7108 (#12992) 2025-12-03 19:43:29 -08:00
openai-moe-iswa.cpp ggml update to b7108 (#12992) 2025-12-03 19:43:29 -08:00
openelm.cpp ggml update to b7108 (#12992) 2025-12-03 19:43:29 -08:00
orion.cpp ggml update to b7108 (#12992) 2025-12-03 19:43:29 -08:00
pangu-embedded.cpp ggml update to b7108 (#12992) 2025-12-03 19:43:29 -08:00
phi2.cpp ggml update to b7108 (#12992) 2025-12-03 19:43:29 -08:00
phi3.cpp ggml update to b7108 (#12992) 2025-12-03 19:43:29 -08:00
plamo.cpp ggml update to b7108 (#12992) 2025-12-03 19:43:29 -08:00
plamo2.cpp ggml update to b7108 (#12992) 2025-12-03 19:43:29 -08:00
plm.cpp ggml update to b7108 (#12992) 2025-12-03 19:43:29 -08:00
qwen.cpp ggml update to b7108 (#12992) 2025-12-03 19:43:29 -08:00
qwen2.cpp ggml update to b7108 (#12992) 2025-12-03 19:43:29 -08:00
qwen2moe.cpp ggml update to b7108 (#12992) 2025-12-03 19:43:29 -08:00
qwen2vl.cpp ggml update to b7108 (#12992) 2025-12-03 19:43:29 -08:00
qwen3.cpp ggml update to b7108 (#12992) 2025-12-03 19:43:29 -08:00
qwen3moe.cpp ggml update to b7108 (#12992) 2025-12-03 19:43:29 -08:00
qwen3next.cpp ggml update to b7108 (#12992) 2025-12-03 19:43:29 -08:00
qwen3vl-moe.cpp ggml update to b7108 (#12992) 2025-12-03 19:43:29 -08:00
qwen3vl.cpp ggml update to b7108 (#12992) 2025-12-03 19:43:29 -08:00
refact.cpp ggml update to b7108 (#12992) 2025-12-03 19:43:29 -08:00
rnd1.cpp ggml update to b7108 (#12992) 2025-12-03 19:43:29 -08:00
rwkv6-base.cpp ggml update to b7108 (#12992) 2025-12-03 19:43:29 -08:00
rwkv6.cpp ggml update to b7108 (#12992) 2025-12-03 19:43:29 -08:00
rwkv6qwen2.cpp ggml update to b7108 (#12992) 2025-12-03 19:43:29 -08:00
rwkv7-base.cpp ggml update to b7108 (#12992) 2025-12-03 19:43:29 -08:00
rwkv7.cpp ggml update to b7108 (#12992) 2025-12-03 19:43:29 -08:00
seed-oss.cpp ggml update to b7108 (#12992) 2025-12-03 19:43:29 -08:00
smallthinker.cpp ggml update to b7108 (#12992) 2025-12-03 19:43:29 -08:00
smollm3.cpp ggml update to b7108 (#12992) 2025-12-03 19:43:29 -08:00
solar.cpp ggml update to b7108 (#12992) 2025-12-03 19:43:29 -08:00
stablelm.cpp ggml update to b7108 (#12992) 2025-12-03 19:43:29 -08:00
starcoder.cpp ggml update to b7108 (#12992) 2025-12-03 19:43:29 -08:00
starcoder2.cpp ggml update to b7108 (#12992) 2025-12-03 19:43:29 -08:00
t5-dec.cpp ggml update to b7108 (#12992) 2025-12-03 19:43:29 -08:00
t5-enc.cpp ggml update to b7108 (#12992) 2025-12-03 19:43:29 -08:00
wavtokenizer-dec.cpp ggml update to b7108 (#12992) 2025-12-03 19:43:29 -08:00
xverse.cpp ggml update to b7108 (#12992) 2025-12-03 19:43:29 -08:00