Muse-Glimmer-30B-CoreAI / gpu-pipelined

Commit History

fix: declare <|eot|> as a stop token — the bundle never terminated
226f682
verified

mlboydaisuke commited on

Muse-Glimmer-30B text decoder -> Core AI: decode int4hu (--head-sym), token-exact vs fp16 oracle, 26.69 tok/s on M4 Max
d284183
verified

mlboydaisuke commited on