Gemma-4-12B-CoreAI / gpu-pipelined

Commit History

chat-EOS fix: eos_token -> <turn|> (clean stop in generic apps)
5623d64
verified

mlboydaisuke commited on

chat-EOS fix: eos_token -> <turn|> (clean stop in generic apps)
2c38bf9
verified

mlboydaisuke commited on

Gemma 4 12B: drop simple-kernel gemma4_12b_qat_decode_int8lin_msdpa (superseded by _g8)
d619e32
verified

mlboydaisuke commited on

Gemma 4 12B: gemma4_12b_qat_decode_int4linsym_msdpa_g8 (higher-occupancy decode bundle)
34ccf9a
verified

mlboydaisuke commited on

Gemma 4 12B: gemma4_12b_qat_decode_int8lin_msdpa_g8 (higher-occupancy decode bundle)
d1f03bb
verified

mlboydaisuke commited on

Gemma 4 12B: gemma4_12b_qat_decode_int8lin_msdpa (metal-sdpa decode bundle)
99f1dbb
verified

mlboydaisuke commited on