Update README.md
Browse files
README.md
CHANGED
|
@@ -4,7 +4,7 @@ emoji: 🧩
|
|
| 4 |
colorFrom: indigo
|
| 5 |
colorTo: purple
|
| 6 |
sdk: gradio
|
| 7 |
-
sdk_version:
|
| 8 |
app_file: app.py
|
| 9 |
pinned: false
|
| 10 |
short_description: Profile adapter compatibility and VRAM cost for models
|
|
@@ -21,4 +21,4 @@ This Hugging Face Space serves as a production-grade developer environment to pr
|
|
| 21 |
- **VRAM & Resource Calculator**: Calculate precise infrastructure footprints, including KV Cache overhead and multi-tenant scaling factors across various quantization levels (FP16, INT8, INT4).
|
| 22 |
|
| 23 |
## Technical Implementation
|
| 24 |
-
The application uses **Gradio** for the interactive interface, **huggingface_hub** for metadata retrieval, and **Plotly** for high-fidelity architectural visualizations. It focuses on structural and resource profiling, abstracting away the underlying tensor computations for rapid prototyping.
|
|
|
|
| 4 |
colorFrom: indigo
|
| 5 |
colorTo: purple
|
| 6 |
sdk: gradio
|
| 7 |
+
sdk_version: 6.15.2
|
| 8 |
app_file: app.py
|
| 9 |
pinned: false
|
| 10 |
short_description: Profile adapter compatibility and VRAM cost for models
|
|
|
|
| 21 |
- **VRAM & Resource Calculator**: Calculate precise infrastructure footprints, including KV Cache overhead and multi-tenant scaling factors across various quantization levels (FP16, INT8, INT4).
|
| 22 |
|
| 23 |
## Technical Implementation
|
| 24 |
+
The application uses **Gradio** for the interactive interface, **huggingface_hub** for metadata retrieval, and **Plotly** for high-fidelity architectural visualizations. It focuses on structural and resource profiling, abstracting away the underlying tensor computations for rapid prototyping.
|