ceos/unsloth
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
unsloth/scripts
History
Daniel Han 9eed2bdfa3 Fix quantized-load LoRA bake, prequant family exclusions and outpaint canvas 
Six review findings across the Images page and model scanning:

- The quantized (int8/fp8) load path can only attach LoRA adapters
  before quantization, but the frontend load request had no loras field,
  so every generation after such a load was rejected and each reload
  repeated it. Send the selection with the load.
- build_prequant_checkpoint passed no family to the scheme exclusions
  while recording the family in metadata, so a Qwen int8 artifact baked
  the short-M text-stream linears and was then rejected wholesale by the
  loader's family-keyed check.
- Registering a bare single-file checkpoint directory produced no On
  Device row even though the images loader can load it; only its parent
  worked. Admit that shape when nothing else matched.
- Unload left the Reapply target set, so the repair path was skipped and
  Reapply reloaded the ejected model. Clear it, as the video page does.
- Both FLUX.2 bases were trusted for training but not inference, so
  Deploy to Create rejected every FLUX.2 adapter.
- Outpaint allocated the grown canvas before downscaling, exceeding the
  browser canvas area cap on a large photo; an over-cap canvas is
  unusable, so Extend silently posted a fully transparent image and
  mask. Scale the source first.
2026-07-26 08:12:01 +00:00
..
data CI: scope GITHUB_TOKEN permissions, add MLX CI, unblock ~60 skipped tests (#5312) 2026-05-11 03:19:13 -07:00
build_prequant_checkpoint.py Fix quantized-load LoRA bake, prequant family exclusions and outpaint canvas 2026-07-26 08:12:01 +00:00
build_te_prequant_checkpoint.py Extend the fp8 TE quant to HiDream's Llama text_encoder_4 2026-07-18 07:55:24 +00:00
build_whisper_cpp.sh Studio: add local speech-to-text dictation engine (#7095) 2026-07-23 01:39:03 -07:00
check_frontend_dep_removal.py Reduce and tighten code comments and docstrings repo-wide (#6095) 2026-06-08 23:09:51 -07:00
check_new_install_scripts.py Reduce and tighten code comments and docstrings repo-wide (#6095) 2026-06-08 23:09:51 -07:00
compare_engines.py Studio diffusion (Phase 7): accuracy-preserving speed pass (2.2x via GGUF compile) (#6690) 2026-07-01 15:31:50 -03:00
compile_probe.py Studio diffusion (Phase 7): accuracy-preserving speed pass (2.2x via GGUF compile) (#6690) 2026-07-01 15:31:50 -03:00
diffusion_bench.py Tighten comments in the image stack tests and scripts 2026-07-12 12:21:14 +00:00
diffusion_quality.py Tighten comments in the image stack tests and scripts 2026-07-12 12:21:14 +00:00
enforce_kwargs_spacing.py Reduce and tighten code comments and docstrings repo-wide (#6095) 2026-06-08 23:09:51 -07:00
fbcache_flux_probe.py Tighten comments in the image stack tests and scripts 2026-07-12 12:21:14 +00:00
fp8_overflow_check.py Tighten comments in the image stack tests and scripts 2026-07-12 12:21:14 +00:00
image_speedmem_bench.py Reset the step cache before every bench generation to match production 2026-07-11 07:55:01 +00:00
install_gemma4_mlx.sh Update Install Scripts (#5968) 2026-06-03 05:39:42 -07:00
install_qwen3_6_mlx.sh Update Install Scripts (#5968) 2026-06-03 05:39:42 -07:00
install_rocm_wsl_strixhalo.sh Replace standalone Studio wording with Unsloth (#7221) 2026-07-19 00:47:04 -07:00
int8_linear_probe.py Studio diffusion (Phase 14): fix int8 dense quant on Flux / Qwen (skip M=1 modulation linears) (#6716) 2026-07-01 15:41:49 -03:00
leverage_probe.py Studio diffusion (Phase 7): accuracy-preserving speed pass (2.2x via GGUF compile) (#6690) 2026-07-01 15:31:50 -03:00
lint_workflow_triggers.py Reduce and tighten code comments and docstrings repo-wide (#6095) 2026-06-08 23:09:51 -07:00
lockfile_supply_chain_audit.py Replace standalone Studio wording with Unsloth (#7221) 2026-07-19 00:47:04 -07:00
notebook_to_python.py Reduce and tighten code comments and docstrings repo-wide (#6095) 2026-06-08 23:09:51 -07:00
notebook_validator.py fix: pin torchcodec for torch 2.10 and warn on ABI mismatch (#7299) 2026-07-23 19:12:52 -07:00
nvfp4_probe.py Studio diffusion (Phase 8): opt-in fast transformer (torchao int8/fp8/fp4 on a dense source) (#6694) 2026-07-01 15:36:43 -03:00
nvfp4_t211_probe.py Fix diffusion training validation, dataset upload atomicity, and LoRA error mapping 2026-07-04 03:17:12 -03:00
perf_levers_probe.py Tighten comments in the image stack tests and scripts 2026-07-12 12:21:14 +00:00
perf_verify.py Studio diffusion (Phase 7): accuracy-preserving speed pass (2.2x via GGUF compile) (#6690) 2026-07-01 15:31:50 -03:00
prequant_probe.py Studio diffusion (Phase 9): pre-quantized transformer loading (#6700) 2026-07-01 15:37:53 -03:00
quant_probe.py Studio diffusion (Phase 8): opt-in fast transformer (torchao int8/fp8/fp4 on a dense source) (#6694) 2026-07-01 15:36:43 -03:00
run_ruff_format.py Reduce and tighten code comments and docstrings repo-wide (#6095) 2026-06-08 23:09:51 -07:00
scan_npm_packages.py Replace standalone Studio wording with Unsloth (#7221) 2026-07-19 00:47:04 -07:00
scan_npm_packages_baseline.json scan_packages: key baseline on matched-code hash so payloads in baselined files are not auto-suppressed (#6552) 2026-07-01 04:03:59 -07:00
scan_packages.py CI: baseline the fastapi/gguf scan findings for the studio dependency set 2026-07-02 02:04:28 +00:00
scan_packages_baseline.json Merge origin/main into image-generation (PR #6763) 2026-07-25 00:34:38 -07:00
sd_cpp_smoke.py Studio diffusion (Phase 6): img2img / inpaint / edit / LoRA / upscale on the native engine (#6680) 2026-07-01 15:18:38 -03:00
sparse_accum_probe.py Fix diffusion training validation, dataset upload atomicity, and LoRA error mapping 2026-07-04 03:17:12 -03:00
stamp_studio_release.py Replace standalone Studio wording with Unsloth (#7221) 2026-07-19 00:47:04 -07:00
sync_allow_scripts_pins.py Studio: auto-sync allowScripts pins after dependency bumps (#6136) 2026-06-10 02:35:37 -07:00
uninstall.ps1 Merge origin/main into image-generation (PR #6763) 2026-07-25 00:34:38 -07:00
uninstall.sh Merge origin/main into image-generation (PR #6763) 2026-07-25 00:34:38 -07:00
verify_comment_only_diff.py Reduce and tighten code comments and docstrings repo-wide (#6095) 2026-06-08 23:09:51 -07:00
verify_import_hoist.py studio: tool calling for DeepSeek (R1/V3/V3.1), GLM 4.x, Kimi K2 on safetensors + MLX (#5624) 2026-07-06 15:40:46 -07:00
verify_prequant_backend.py Tighten comments in the image stack tests and scripts 2026-07-12 12:21:14 +00:00
video_quality.py Tighten comments in the image stack tests and scripts 2026-07-12 12:21:14 +00:00