Disable Tesseract by default for GPU-first benchmark runs

Deploy CUDA-enforced runtime changes for OCR

Enforce strict GPU startup + runtime checks

Hard-fail non-CUDA model placements in strict mode

Fix startup indentation and keep strict CUDA policy in sync

Fix README content mapping

Fix build indentation and enforce CUDA-only path

Repair README content and re-sync Space files

Add strict CUDA validation and CUDA-only runtime docs

Enforce strict CUDA path for local OCR inference

Force ZeroGPU CUDA inference path and direct-model device hardening

Harden image/model input parsing for stable Space runs

Fix comparison runtime robustness for zero-gpu and API route

Hardened precheck and runtime recovery

Fix local transformer bootstrap and dependency baseline

Fix local inference runner and result collection

Update gradio version for runtime import compatibility

Resolve huggingface-hub version conflict for transformers

Patch: fix dependency/runtime fallbacks for OCR models

Fix dependency compatibility for runtime startup

Fix syntax error in pipeline dtype loop

Fix requirements conflict for transformers build

Compatibility fixes for local OCR models

Add cyttic OCR models to registry

Use local ZeroGPU offline inference only

Add PaddleOCR + DeepSeek OCR models and raise default output token budget

Scope GPU lease to active inference runs

Remove persistent GPU warmup; rely on sleep timeout for idle GPU control

Treat tesseract as low VRAM workload in scheduler

Add compute-mode scheduling docs and final notes

ZeroGPU compute-mode scheduling + safety caps

Make audioop-lts conditional for py3.10 ZeroGPU compatibility

Handle starlette request-first TemplateResponse for gradio root

Fix gradio template response argument handling

Simplify TemplateResponse shim context normalization to plain dict

Harden TemplateResponse shim for mapping-context calls

Fix template context injection in Starlette Jinja shim

Re-add scoped safe Jinja2 get_template shim to fix dict template name

Remove gradio template monkeypatches to avoid root template runtime errors

Replace unavailable pyaudioop with audioop-lts for Python 3.13

Add pyaudioop for Python 3.13 import compatibility

Keep safe get_template only; remove safe TemplateResponse monkeypatch

Remove Jinja template monkeypatches, keep chainable undefined fallback

Debug template context payload once

Remove debug prints after template fix

Fix template debug patch indentation

Add one-time template context debug logging

Set Gradio Jinja undefined to ChainableUndefined

Fix safe template context assignment precedence

Fix gradio template context injection for zero gpu space