2.4.0

llama.cpp + new GGML_CUDA
LLAMA_CUDA env var to set if llama.cpp is compiled with CUDA

2.3.2

llama.cpp update + more llava yaml

2.3.1

params and prompt files renamed

2.3.0

New bringup format using YAML files with params

2.2.5

llama.cpp updated

2.2.4

llama.cpp updated

2.2.3

llama.cpp updated

2.2.2

stopping words fixed, replacing "\n" by "\n"

2.2.1

stopping_words param

2.2.0

New params and configurations for create_llama_launch:

• system_prompt
• system_prompt_file
• system_prompt_type
• model
• lora_base
• mmproj