Advanced quantization toolkit for LLMs and VLMs. Support for WOQ, MXFP4, NVFP4, GGUF, Adaptive Schemes and seamless integration with Transformers, vLLM, SGLang, and llm-compressor
-
Updated
Dec 23, 2025 - Python
#
nvfp4
Here are 3 public repositories matching this topic...
LLM fine-tuning with LoRA + NVFP4/MXFP8 on NVIDIA DGX Spark (Blackwell GB10)
deep-learning pytorch nvidia lora quantization fine-tuning blackwell llm nvfp4 dgx-spark transformer-engine mxfp8
-
Updated
Dec 22, 2025 - Python
ARCQuant: Boosting Fine-Grained Quantization with Augmented Residual Channels for LLMs
-
Updated
Dec 14, 2025 - Cuda
Improve this page
Add a description, image, and links to the nvfp4 topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the nvfp4 topic, visit your repo's landing page and select "manage topics."