ollama/model/models
Michael Yang ad95d5b30b
use split activations when possible (#12293)
* use ggml_*_split activations when possible

* forward qkv
2025-09-16 09:51:19 -07:00
..
bert embed: cleanup (#12299) 2025-09-16 09:48:42 -07:00
gemma2 use split activations when possible (#12293) 2025-09-16 09:51:19 -07:00
gemma3 use split activations when possible (#12293) 2025-09-16 09:51:19 -07:00
gemma3n use split activations when possible (#12293) 2025-09-16 09:51:19 -07:00
gptoss use split activations when possible (#12293) 2025-09-16 09:51:19 -07:00
llama use split activations when possible (#12293) 2025-09-16 09:51:19 -07:00
llama4 use split activations when possible (#12293) 2025-09-16 09:51:19 -07:00
mistral3 use split activations when possible (#12293) 2025-09-16 09:51:19 -07:00
mllama use split activations when possible (#12293) 2025-09-16 09:51:19 -07:00
qwen2 use split activations when possible (#12293) 2025-09-16 09:51:19 -07:00
qwen3 use split activations when possible (#12293) 2025-09-16 09:51:19 -07:00
qwen25vl use split activations when possible (#12293) 2025-09-16 09:51:19 -07:00
models.go model: implement bert in ollama engine (#9080) 2025-09-15 15:35:59 -07:00