Over 60 figures and diagrams of LLMs, quantization, low-rank adapters (LoRA), and chat templates FREE TO USE in your blog posts, slides, presentations, or papers.
RTL implementation of a performance/area optimized bfloat16 adder and multiplication.
A flexible utility for converting tensor precision in PyTorch models and safetensors files, enabling efficient deployment across various platforms.
Converts a floating-point number or hexadecimal representation of a floating-point numbers into various formats and displays them into binary/hexadecimal.
Python implementations for multi-precision quantization in computer vision and sensor fusion workloads, targeting the XR-NPE Mixed-Precision SIMD Neural Processing Engine. The code includes visual inertial odometry (VIO), object classification, and eye gaze extraction code in FP4, FP8, Posit4, Posit8, and BF16 formats.
Auto GGUF Converter for HuggingFace Hub Models with Multiple Quantizations (GGUF Format)
A Gradio-powered web interface for performing advanced OCR tasks using the DeepSeek-OCR model. This experimental app leverages Hugging Face Transformers to process images for text extraction, document conversion, figure parsing, and object localization.
Matrix-free 3D SIMP topology optimization with fused gather-GEMM-scatter CUDA kernels on NVIDIA RTX 4090. Companion code for arXiv:2604.18020.
Systematic 24-hour benchmark study of Qwen3.6-27B inference on dual NVIDIA RTX PRO 6000 Blackwell SM120 (TP=2). 8 experiments comparing repne/vllm fork vs upstream vLLM across FP8/BF16/NVFP4/Q8_0 quants and MTP/DFlash speculative decoding. Peak: 2,083 tok/s at c=32. Quality: KLD vs BF16 = 0.0018 (noise floor).
🖼️ Enhance text extraction and document parsing with the DeepSeek-OCR model through this Gradio web interface optimized for NVIDIA GPUs.
Add a description, image, and links to the bf16 topic page so that developers can more easily learn about it.
To associate your repository with the bf16 topic, visit your repo's landing page and select "manage topics."