Issues

• #462 stage D: one-job-per-GPU MCP text, docs and UI

  dkackman/diffusers-workflow#678 · opened on Oct 7, 2026

• #462 stage C: affinity, per-worker memory and cache

  dkackman/diffusers-workflow#677 · opened on Oct 7, 2026

• #462 stage B: worker pool and VRAM-aware dispatcher

  dkackman/diffusers-workflow#676 · opened on Oct 7, 2026
  8

• idea (parked): tiled latent fusion for tile-trained LTX-2.5 IC-LoRAs (Refine-Details, Restore, Deblur)

  dkackman/diffusers-workflow#597 · opened on Oct 5, 2026
  1

• idea: support multiple GPUs for concurrent workload execution

  dkackman/diffusers-workflow#462 · opened on Sep 25, 2026
  5