AstrAI

Files

T

History

ViperEkura 432dfec3c2 refactor: collapse fp8 recipe hierarchy and state property layers

- Merge DelayedScaling/DynamicScaling and the abstract FP8Recipe base into one FP8Recipe dataclass with a dynamic flag; dispatch now reads cfg.recipe.dynamic instead of isinstance checks
- Drop the _ActiveOrDefault descriptor and the FP8State property views; the persistent defaults are plain default_* attributes and get_weight_meta takes the active recipe explicitly
- Convert FP8TensorMeta to a NamedTuple of the three per-operand rings
- Update tests to the new API; the autocast context test now asserts _active_config push/restore directly

2026-08-31 14:24:51 +08:00

data

refactor: unify CUDA skip guards in tests

2026-08-22 21:08:06 +08:00

extension

refactor: collapse fp8 recipe hierarchy and state property layers

2026-08-31 14:24:51 +08:00

inference

perf: fill steady-state decode input ids via d2d copy

2026-08-31 14:24:51 +08:00

module

test: refactor tests and fix inference edge cases