docs: remove studio link and add paradigm info to API tab

docs: add paradigm explanations under tabs

fix: support newer DynamicCache attribute structure in transformers 5.8

docs: add cURL equivalent and rename Swagger tab

fix: set python_version to 3.12 for Pyarmor ABI compatibility

fix: move pyarmor runtime to root so app.py can import it

chore: encrypt core math operations for IP protection

chore: setup lfs for pyarmor binaries

Fix Phase Attention Benchmark to simulate GQA 2 KV heads

Add torch.inference_mode to stop backward graph creeping

Fix Phase Attention Benchmark to simulate 24 layers

fix: add missing typing import

fix: Implement infinite O(1) chunked online softmax phase sweep

feat: Add True O(1) Phase Attention benchmark endpoint

perf: implement matrix trick for O(1) peak VRAM via einsum

fix: total_memory attribute typo

feat: add real empirical benchmark harness with /run_benchmark endpoint

docs: update Swagger tab with complete PowerShell, Python, JS, and cURL 2-step REST examples

fix: configure clean chat template and hybrid RIF sliding window on T4 GPU

fix: enable KalpanaHybridCacheLayer in KalpanaDynamicCache for fluent generation

fix: add system prompt, top_p, and repetition_penalty to prevent small model loop

fix: restore native Gradio 5 launcher for ZeroGPU prestart hooks

feat: add FastAPI server with Live Swagger UI, OpenAI endpoints, and CORS

feat: upgrade holographic resolution to 2048 bands on NVIDIA A100

fix: bridge KalpanaRIFTensor to native kalpana.core kernel without kwargs mismatch

fix: bundle kalpana module and clean requirements.txt

chore: enforce strict binary SDK kernel with zero math in Python

chore: sanitize core.py and obfuscate internal parameters

feat: integrate KalpanaDynamicCache into all 24 layers of Qwen2.5 on ZeroGPU

feat: integrate KalpanaDynamicCache into all 24 layers of Qwen2.5 on ZeroGPU

feat: integrate KalpanaDynamicCache into all 24 layers of Qwen2.5 on ZeroGPU

feat: integrate KalpanaDynamicCache into all 24 layers of Qwen2.5 on ZeroGPU

feat: integrate KalpanaDynamicCache into all 24 layers of Qwen2.5 on ZeroGPU

feat: integrate KalpanaDynamicCache into all 24 layers of Qwen2.5 on ZeroGPU

feat: integrate KalpanaDynamicCache into all 24 layers of Qwen2.5 on ZeroGPU

feat: integrate KalpanaDynamicCache into all 24 layers of Qwen2.5 on ZeroGPU

feat: integrate KalpanaDynamicCache into all 24 layers of Qwen2.5 on ZeroGPU

feat: integrate KalpanaDynamicCache into all 24 layers of Qwen2.5 on ZeroGPU

feat: integrate KalpanaDynamicCache into all 24 layers of Qwen2.5 on ZeroGPU

feat: integrate KalpanaDynamicCache into all 24 layers of Qwen2.5 on ZeroGPU

feat: integrate KalpanaDynamicCache into all 24 layers of Qwen2.5 on ZeroGPU

feat: integrate KalpanaDynamicCache into all 24 layers of Qwen2.5 on ZeroGPU

feat: integrate KalpanaDynamicCache into all 24 layers of Qwen2.5 on ZeroGPU

feat: integrate KalpanaDynamicCache into all 24 layers of Qwen2.5 on ZeroGPU

feat: integrate KalpanaDynamicCache into all 24 layers of Qwen2.5 on ZeroGPU

feat: integrate KalpanaDynamicCache into all 24 layers of Qwen2.5 on ZeroGPU

feat: integrate KalpanaDynamicCache into all 24 layers of Qwen2.5 on ZeroGPU

fix: resolve AttributeError on llm.DEFAULT_MODELS in Gradio UI startup

fix: restore list_models optional request parameter

fix: update list_models request signature