Hugging Face· PlatformDeveloper tool

Introducing AutoRound: Intel’s Advanced Quantization for LLMs and VLMs

Intel introduces AutoRound, a new quantization tool for LLMs and VLMs that uses signed gradient descent to optimize weight rounding and clipping, supporting low-bit quantization with minimal accuracy loss.

From the source

AutoRound is a weight-only post-training quantization (PTQ) method developed by Intel.

huggingface.co

Announced

29 Apr 2025 00:00 UTC

Detected

03 Aug 2026 21:12 UTC (+461d after)