biondizzle d3b772196d E3: Implement DSV4Model — full model class ...

- Token embedding → N×TransformerLayer → RMSNorm → lm_head
- decode_step: single token decode with mHC state management
- forward: prefill path (T tokens)
- Cache handle acquisition per layer
- mHC state initialization from embedding
- Weight loading TODO (deferred to loader/)

2026-05-30 21:15:57 +00:00

..

__init__.py

Restructure: cutedsl/ -> dsv4/ with proper layering

2026-05-21 17:30:44 +00:00

config.py

Layer dispatch: config, schedule, attention/FFN sub-blocks, TransformerLayer

2026-05-21 23:11:09 +00:00

dsv4.py

E3: Implement DSV4Model — full model class

2026-05-30 21:15:57 +00:00

layer_schedule.py

Layer dispatch: config, schedule, attention/FFN sub-blocks, TransformerLayer

2026-05-21 23:11:09 +00:00

layer.py

Fix layer construction: match existing API signatures, add RMSNorm impl

2026-05-21 23:31:58 +00:00

mtp.py

Restructure: cutedsl/ -> dsv4/ with proper layering

2026-05-21 17:30:44 +00:00

sampler.py

Restructure: cutedsl/ -> dsv4/ with proper layering

2026-05-21 17:30:44 +00:00