LTX2.5-Studio / tests /test_device_path.py

Commit History

2 days ago

  1. fix: no entry can sample on an MPS PyTorch that fails the numerics self-test: build_local_runner applies the app's gate on mps, so scripts/local_generate.py --device mps exits refused (2) before loading anything, and the remedy names the README's floor, PyTorch 2.14 (#11)⁠

    Unverified signature
    444bc2b
  2. fix: a bad MPS watermark pair stops the app's MPS start in its own words before the numerics self-test runs, and every numerics gate checks the pair first, so it is never reported as a PyTorch that computes wrongly (#10)⁠

    Unverified signature
    e664ad9

3 days ago

  1. fix: the generation-disabled message no longer says 70 GB either way, and a sound file given as the video is pinned as refused before dispatch⁠

    Unverified signature
    aacd299
  2. fix: the local runner never restores a failed run's adapter, preflights a converting load at its real cost, and a real-sized snapshot override goes through it⁠

    Unverified signature
    12a7ca3
  3. fix: the app starts on mps/cpu with the GGUF layout: start-up checks what the local runner loads, not the Space's allow-list⁠

    Unverified signature
    dd7574c
  4. feat: real weights on MPS/CPU go to the local runner, chosen by the one device resolver; the tiny snapshot keeps the resident StageRunner⁠

    Unverified signature
    e6b3ade
  5. feat: one device resolver — CUDA on ZeroGPU, MPS/CPU by opt-in, and no silent 70 GB load anywhere else⁠

    Unverified signature
    0ed2aa1