LTX2.5-Studio / tests /test_local_runtime.py

Commit History

3 days ago

  1. fix: the bar names what is happening: a staged local run's loads read "loading the model" at the bar's current position until the denoise really starts, and a single pass that decodes inside the pipeline call (the conv decoder, "Fast") reads "decoding the frames" after its last step (#12)⁠

    Unverified signature
    aeab028
  2. 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

4 days ago

  1. fix: a run never inherits another run's adapter: before anything is attached, every run removes any adapter left on the model (on its components, or kept for a released staged transformer), and a run whose leftover cannot be removed is refused as an adapter failure and never sampled

    Unverified signature
    d9da392
  2. fix: after the local runner frees memory, the memory check judges the gauge once it has stopped falling, and a check that fails reads it again before refusing⁠

    Unverified signature
    ba2d582
  3. fix: the local script leaves the change level to the mode and writes the run record into its JSON, and the record names the device that ran⁠

    Unverified signature
    419e0a5
  4. fix: everything a user reads after Generate is in the UI's words, and audio too short for the set length is refused in them⁠

    Unverified signature
    8a7fa0c
  5. feat: one stage graph for the Space and the local runner: the local runner is a StageRunner that supplies residency through one seam⁠

    Unverified signature
    c712e7e
  6. fix: the local runner preflights adapters and frees memory after a failure, keeps CPU weights' pages, sizes auto-duration as the head does; the worker logs a small GPU slice and the override fetches nothing⁠

    Unverified signature
    f851454
  7. 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
  8. feat: video to video is a variation of the user's clip, noised to a level and denoised along the schedule's tail⁠

    Unverified signature
    85405e9
  9. fix: a derived pipeline shares the loaded modules without casting them, so the audio modes run with a quantized transformer⁠

    Unverified signature
    b12415f
  10. fix: audio conditioning has its own noise level and schedule, so audio_to_video and audio_to_audio sample the video like every other mode⁠

    Unverified signature
    be9c1db
  11. fix: the local runner keeps the checkpoint's float64 RoPE on MPS by computing it on the CPU, after every load⁠

    Unverified signature
    5e4829a
  12. fix: refuse an MPS watermark pair that makes every empty_cache() fail, before anything loads⁠

    Unverified signature
    adad9b6
  13. fix: the local runner gives model-file pages back — the committed gauge no longer counts weights twice⁠

    Unverified signature
    75d0c53
  14. feat: scripts/local_generate.py — one local generation through the app's own generate(), with its memory story⁠

    Unverified signature
    af26f09

5 days ago

  1. feat: a local mps/cpu runner — the text encoder and the transformer are never resident together⁠

    Unverified signature
    2155bf9