Will LinandClaude Fable 5 dd9276d1c8 [train] H3 v5 config: keep-4 checkpoint retention (fp32 saves are ~528 GiB) ...

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

2026-08-14 06:07:13 +00:00

..

datasets

[misc]: consolidate dataset download scripts under examples/datasets/ (#1667)

2026-08-02 14:21:24 -07:00

distill

[train] VSA-H3 DMD2 overfit: per-role backends, VSA metadata wiring, wandb guard

2026-08-09 14:46:58 -07:00

inference

[perf] MiniMax-H3: rank-reduced AdaLN pruned model option (-39% params, -23 GiB VRAM) (#1699)

2026-08-09 12:31:57 -07:00

serving

[infra] Dreamverse 09/14: Add Docker and launch scripts (#1332)

2026-05-12 18:01:11 -07:00

train

[train] H3 v5 config: keep-4 checkpoint retention (fp32 saves are ~528 GiB)

2026-08-14 06:07:13 +00:00

training

[misc]: consolidate dataset download scripts under examples/datasets/ (#1667)

2026-08-02 14:21:24 -07:00