ggml-cpu: enable IBM NNPA Vector Intrinsics (llama/14317) fea8f94 taronaeo slaren commited on Jun 25, 2025
ggml-cpu : split arch-specific implementations (llama/13892) 8c833e9 xctan ggerganov HF Staff commited on Jun 9, 2025
ggml : refactor online repacking (llama/10446) 163128e Djip007 ggerganov HF Staff commited on Dec 7, 2024