Update app.py

Update app.py

Update requirements.txt

Update app.py

Update app.py

Update app.py

Update app.py

Update README.md

Delete README_OLD.md

Delete USER_GUIDE.md

Create app.py

Rename app.py to config.py

Add comprehensive changelog for UI/UX improvement session

Add UI/UX improvements summary documentation

Add comprehensive documentation and user guide

Major UI/UX improvements for better user experience

Fix UI not resetting after cancel - add reset handler

Fix GeneratorExit handling to prevent runtime error

Fix cancel generation feature by removing GeneratorExit handler

Handle GeneratorExit by yielding UI reset and returning cleanly

Simplify GeneratorExit handling - let it propagate and rely on finally block

Fix GeneratorExit handling by re-raising after UI reset

Fix UI state reset after generation cancellation

Fix GeneratorExit exception in cancel generation by adding proper exception handling

bugfix

Improve cancel generation with robust UI state management and orchestrator pattern

Restore cancel generation feature with improved UI integration

Remove cancel generation feature as it didn't work

Restore proper cancel functionality

Test stopping criteria effectiveness

Improve cancel generation responsiveness

Fix cancel generation to gracefully stop ongoing response generation

remove qwen3 30b-a3b and qwen3 next 80b-a3b

Remove AOT indication from UI duration estimate

Remove AOT compilation completely and enable use_cache

Fix dynamic_shapes kwargs to match inputs structure for AOT compilation

Fix AOT compilation dynamic_shapes to match expected arg names for torch.export.export

Update requirements.txt

Update requirements.txt

Add dynamic GPU time estimate indicator to UI

Improve model size detection: replace ad-hoc string parsing with reliable params_b field in MODELS dict

Add qwen 80b-a3b

Set better defaults for free-tier users: Qwen3-1.7B model, 1024 max tokens, search disabled

Adjust duration estimation for H200 performance - reduce conservative estimates

Use actual parameter count for AOT decision instead of string matching

Make AOT compilation conditional for models >= 2B parameters to optimize free tier usage

Add AOT compilation optimization for ZeroGPU acceleration

add 4 20b+ models after enabling dynamic gpu duration

Add dynamic duration calculation for ZeroGPU acceleration

make qwen-4b default