unsloth/studio
Daniel Han be04ba00f4 video/image: honor explicit Speed=off for companions + trim, probe explicit TE kernels, bench fidelity
Address the Codex review round on the video/quant work:

- Companion auto-quant now honors an explicit Speed=off. Both loaders already pin the DiT dense
  under an explicit off (bit-exact reference), but the unset text-encoder / VAE quant still promoted
  to auto and silently fp8/int8'd the companions, breaking the bit-exact request. An UNSET speed
  still auto-quantises; an explicit companion scheme still forces it.
- The HunyuanVideo joint-attention trim is a speed lever (it swaps to the fused SDPA kernel), so gate
  it on a non-off speed tier exactly like the adjacent attention-backend selection -- the off path
  keeps the stock dense-mask attention.
- Explicit torchao text-encoder modes (int8 / fp8_dynamic / nvfp4) now run the same kernel smoke
  test the auto ladder uses. They could clear the capability gate yet fail the real GEMM on a build
  where quantize_ wraps the encoder but the kernel is broken; the caster's try/except only covers the
  cast, not the first forward, so the load would report engaged then crash at generation. Now it
  falls back to dense. Layerwise fp8 has no torchao GEMM, so the probe is a no-op for it.
- The trim pre-hook's fallback restores the caller's original kwargs (it may have emptied the image
  stream / trimmed a text stream before failing), so the stock dense-mask path runs on exactly what
  it expects, matching the empty-prompt guard.
- video_speedmem_bench mirrors the loader: installs the Hunyuan trim before the backend set (gated on
  an active tier) and skips the auto int8 quant when it is the fp8-denied memory fallback and dense
  fits resident, so the shipped/auto rows measure what the loader actually runs.

Tests: TE explicit-mode kernel probe (+ layerwise-fp8 bypass), trim mid-trim restore, and loader-level
speed=off companion suppression + trim skip for both backends. 262 backend tests pass; ruff clean.
2026-07-09 09:24:28 +00:00
..
backend video/image: honor explicit Speed=off for companions + trim, probe explicit TE kernels, bench fidelity 2026-07-09 09:24:28 +00:00
frontend Key image-gen LoRA rows by index so typing a repo id keeps input focus 2026-07-08 07:19:13 +00:00
src-tauri Speed up Studio startup path (#6899) 2026-07-07 18:08:07 -07:00
__init__.py Final cleanup 2026-03-12 18:28:04 +00:00
install_llama_prebuilt.py Studio: stop handing CI/user secrets to downloaded llama.cpp binaries (#6696) 2026-06-27 05:21:05 -07:00
install_node_prebuilt.py Pin isolated Node.js installer to committed sha256 digests (#6625) 2026-06-24 05:47:58 -07:00
install_python_stack.py Studio: exclude mlx-lm 0.31.3 (broke gemma4/qwen3_5 QK-norm load on Apple Silicon) (#6803) 2026-07-06 19:40:06 -07:00
install_sd_cpp_prebuilt.py Studio: classify local video pipelines, harden video preflight, and gate custom-root sd.cpp removal on ownership 2026-07-07 03:15:07 +00:00
LICENSE.AGPL-3.0 Add AGPL-3.0 license to studio folder 2026-03-09 19:36:25 +00:00
node_prebuilt_pins.json Pin isolated Node.js installer to committed sha256 digests (#6625) 2026-06-24 05:47:58 -07:00
package-lock.json ci: advisory lockfile supply-chain audit (no install-script changes) (#5604) 2026-05-19 05:56:56 -07:00
package.json ci: advisory lockfile supply-chain audit (no install-script changes) (#5604) 2026-05-19 05:56:56 -07:00
setup.bat Final cleanup 2026-03-12 18:28:04 +00:00
setup.ps1 [Studio] Add --with-llama-cpp-dir installer flag to reuse a local llama.cpp (#6472) 2026-07-02 22:11:20 +01:00
setup.sh [Studio] Add --with-llama-cpp-dir installer flag to reuse a local llama.cpp (#6472) 2026-07-02 22:11:20 +01:00
Unsloth_Studio_Colab.ipynb Studio Colab: opt-in shareable Cloudflare tunnel link (#6684) 2026-06-26 00:56:23 -07:00