gemma.cpp/evals/testdata
Ray Smith 7b55d41f46 Rewrote flash attention to use BF16, transpose k and v, rewrote the task distribution, increase parallelism on decode, and use double the registers for the core of flash attention.
PiperOrigin-RevId: 868146247
2026-02-13 01:58:48 -08:00
..
holiday_story.txt Rewrote flash attention to use BF16, transpose k and v, rewrote the task distribution, increase parallelism on decode, and use double the registers for the core of flash attention. 2026-02-13 01:58:48 -08:00
quark_1.txt Rewrote flash attention to use BF16, transpose k and v, rewrote the task distribution, increase parallelism on decode, and use double the registers for the core of flash attention. 2026-02-13 01:58:48 -08:00
quark_2.txt Rewrote flash attention to use BF16, transpose k and v, rewrote the task distribution, increase parallelism on decode, and use double the registers for the core of flash attention. 2026-02-13 01:58:48 -08:00
special_relativity.txt Rewrote flash attention to use BF16, transpose k and v, rewrote the task distribution, increase parallelism on decode, and use double the registers for the core of flash attention. 2026-02-13 01:58:48 -08:00
standard_model.txt Rewrote flash attention to use BF16, transpose k and v, rewrote the task distribution, increase parallelism on decode, and use double the registers for the core of flash attention. 2026-02-13 01:58:48 -08:00