Aryan Kumar 21e749156c [fix]: address QAD review findings ...

- Include V2 width/height/num_frames and the train manifest in the step-0
  fingerprint so a dimension change cannot reuse a stale baseline.
- Honor CompressionSpec.first_steps in the V2 rung scope.
- Mark tagged checkpoints weights-only in metadata and teach the exporter
  to resolve and load them, so best/ can be exported.
- Add a tile-64 backward comparison against the STE reference.

2026-10-19 12:16:45 -07:00

..

consistency_model

[feat] Add Clean-history Teacher Forcing and Causal Consistency Distillation (#1505)

2026-07-07 08:13:11 +00:00

distribution_matching

[feat] Port NVFP4 QAT/QAD to modular train framework (#1619)

2026-07-18 15:01:09 -07:00

fine_tuning

[feat] Add end-to-end MMAudio V2A training, inference, and evaluation (#1648)

2026-10-07 04:25:00 -07:00

knowledge_distillation

[fix]: address QAD review findings

2026-10-19 12:16:45 -07:00

rl

[feat] Add Clean-history Teacher Forcing and Causal Consistency Distillation (#1505)

2026-07-07 08:13:11 +00:00

__init__.py

[feat] Add end-to-end MMAudio V2A training, inference, and evaluation (#1648)

2026-10-07 04:25:00 -07:00

base.py

[feat] Add end-to-end MMAudio V2A training, inference, and evaluation (#1648)

2026-10-07 04:25:00 -07:00