OpenTransformer
/

llama.cpp-prismml

Model card Files Files and versions

OpenTransformer commited on Apr 2

Commit

165bcc5

·

verified ·

1 Parent(s): 8f4b822

perf: optimized AVX2 kernel + COM6-inspired matmul dispatch (0.2 -> 3.43 t/s)

Files changed (0) hide show