Create README.md

README.md

@@ -0,0 +1,55 @@
+---
+license: other
+license_name: thestage-ai-proprietary
+library_name: qlip
+tags:
+  - tensorrt
+  - qlip
+  - thestage
+  - diffusion
+  - acceleration
+  - lora
+---
+
+# Precompiled TensorRT Engines by Qlip
+
+Precompiled [Qlip](https://thestage.ai) engines for accelerated diffusion model inference. Base model weights are **not** included.
+
+For supported models, benchmarks, and usage instructions see [ComfyUI-Qlip](https://github.com/TheStageAI/ComfyUI-Qlip).
+
+## Usage
+
+### ComfyUI (automatic download)
+
+In the **Qlip Engines Loader** node, set the `hf_repo` input. Engines are downloaded once and cached locally.
+
+### Manual download
+
+```bash
+pip install huggingface-hub
+huggingface-cli download TheStageAI/<repo-name> \
+    --local-dir ./engines \
+    --include "models/H100/<variant>/*"
+```
+
+## Installation
+
+```bash
+# Qlip core
+pip install 'qlip.core[nvidia]' \
+    --extra-index-url https://thestage.jfrog.io/artifactory/api/pypi/pypi-thestage-ai-production/simple
+
+# elastic_models (LoRA runtime support)
+pip install 'thestage-elastic-models[nvidia]' \
+    --extra-index-url https://thestage.jfrog.io/artifactory/api/pypi/pypi-thestage-ai-production/simple
+```
+
+## Requirements
+
+- NVIDIA GPU with CUDA 12.x
+- TensorRT 10.13.3.9 (must match compilation version)
+- Engines are GPU-architecture specific — recompile after changing hardware
+
+## License
+
+Proprietary. Powered by [TheStage AI](https://thestage.ai).