Regenerate knapsack_cache.zip for instanovo 1.2.2 format

Patch gradio_log.Log in-place for per-session tailing

Disable SSR on launch to fix HF Spaces 500

Loosen depenceny requirements

Ignore Gradio's auto-generated app.pyi stub

Fix queue KeyError by tailing per-session log files in a Log subclass

Refresh greedy-decode log-prob baseline for torch 2.8.0

Isolate application logs per Gradio session

Bump dependencies

Bump spaces to 0.50.2

Make torch version in requirements.txt compatible with ZeroGPU.

Update tests

Retrigger build

Update InstaNovo to v1.2.2 with reproducibility fixes

build(deps): bump the uv group across 1 directory with 12 updates

Remove local Gradio certificate

Handle InstaNovo decoder output changes

Pin Space runtime dependencies

Retrigger build

Bump HF Spaces sdk_version to 5.38.2

Revert "Remove bundled knapsack_cache.zip"

Remove bundled knapsack_cache.zip

Lazy-load models on first prediction for ZeroGPU

Adapt to InstaNovo v1.2.2 API

Fix package configuration for editable install

Update InstaNovo to v1.2.2 with reproducibility fixes

Upgrade to instanovo 1.1.4

Upgrade to InstaNovo v1.1.3 with new diffusion checkpoint

build: update requirements

fix: handle upper, lower and mixed case file extensions

docs: update citation

Add thumbnail

docs: move Notes section lower

build: add knapsack_cache to .gitignore

build: add allowed_paths to demo.launch

build: unzip knapsack_cache.zip if it exists

build: Add knapsack_cache.zip to LFS

build: change svg to png

docs: solid color green

docs: white is not an allowed color

docs: update README

docs: add note about ZeroGPU

fix: pass full residue set to knapsack

docs: update Notes

fix: fix showing of examples and transformer decoding method

feat: adding support for IN+

fix: create temporary directory for Gradio assets

build: add @spaces.GPU decorator

build: don't add qoutes around cu124

build: install cu124 extras