LaunchDevelopers
22 hours ago
DeepSeek V4 support merged into llama.cpp
Pull request #24162 adding DeepSeek V4 support has been merged into llama.cpp, enabling local inference. Users can now compile and run GGUF quantizations.
Pull request #24162 adding DeepSeek V4 support has been merged into llama.cpp, enabling local inference. Users can now compile and run GGUF quantizations.