| .. |
|
attention_d64.splash
|
ai: the AI hub gives way to the UI, smaller models, vision and speech
|
2026-10-13 12:26:21 +02:00 |
|
cooperative_test.splash
|
ai: the AI hub gives way to the UI, smaller models, vision and speech
|
2026-10-13 12:26:21 +02:00 |
|
elementwise.splash
|
ai: the AI hub gives way to the UI, smaller models, vision and speech
|
2026-10-13 12:26:21 +02:00 |
|
gemm.splash
|
ai: the AI hub gives way to the UI, smaller models, vision and speech
|
2026-10-13 12:26:21 +02:00 |
|
gemm_int8.splash
|
ai: the AI hub gives way to the UI, smaller models, vision and speech
|
2026-10-13 12:26:21 +02:00 |
|
gemm_phone.splash
|
ai: the AI hub gives way to the UI, smaller models, vision and speech
|
2026-10-13 12:26:21 +02:00 |
|
kokoro.splash
|
ai: the AI hub gives way to the UI, smaller models, vision and speech
|
2026-10-13 12:26:21 +02:00 |
|
llm.splash
|
on-device AI: LLM decode updates recurrent state in place (no per-layer per-token copies, checkpoint mode unchanged); opt-in GEMV variants (MAKEPAD_LLM_GEMV) and int8 vision-tower GEMMs (MAKEPAD_VISION_GEMM); not yet phone-benchmarked
|
2026-10-21 09:02:57 +02:00 |
|
textdet.splash
|
ai: the AI hub gives way to the UI, smaller models, vision and speech
|
2026-10-13 12:26:21 +02:00 |
|
vision.splash
|
ai: the AI hub gives way to the UI, smaller models, vision and speech
|
2026-10-13 12:26:21 +02:00 |
|
whisper.splash
|
ai: the AI hub gives way to the UI, smaller models, vision and speech
|
2026-10-13 12:26:21 +02:00 |