Aryan Kumar cc9bfd069d [perf]: Load H3 DiT weights onto CUDA, not CPU ...

GB10 unified memory made the CPU-then-copy path take minutes for
the 35B FastH3 transformer. When host offload is off, read
safetensors onto the accelerator.

2026-08-30 23:27:24 -07:00

..

add_pipeline.md

[docs]: unify community links on the README Slack invite (#1643)

2026-07-25 17:26:58 -07:00

architecture.md

[misc] Rename MatrixGame to MatrixGame2 (#1357)

2026-05-17 22:57:03 -07:00

cli.md

[feat] [3/n] Improve API: extend support to cli (#1226)

2026-04-14 15:20:47 -07:00

comfyui.md

[docs] port to mkdocs (#855)

2025-11-04 14:31:56 -08:00

configuration.md

[feat] [3/n] Improve API: extend support to cli (#1226)

2026-04-14 15:20:47 -07:00

gen3c.md

[misc]: standardize install instructions on uv pip install (#1279)

2026-05-02 12:45:50 -07:00

inference_quick_start.md

[docs]: batched docs cleanup (landing page, links, requirements, nav) (#1644)

2026-08-02 18:03:26 -07:00

offloading.md

[perf]: Load H3 DiT weights onto CUDA, not CPU

2026-08-30 23:27:24 -07:00

optimizations.md

[perf] Align FastH3 optimized inference profile (#1748)

2026-08-23 02:01:03 -07:00

support_matrix.md

[feat] Add MiniMax H3 MLX T2VA inference (#1770)

2026-08-28 12:54:33 -07:00