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

..

installation

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

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

installation.md

[docs]: add a maintained inference cookbook (#1290)

2026-08-21 01:53:44 -05:00

quick_start.md

[docs]: add a maintained inference cookbook (#1290)

2026-08-21 01:53:44 -05:00

v1_api.md

[feat] [4/n] Improve API: refactor sampling param and merge with presets (#1234)

2026-04-16 14:10:02 -07:00