Hi, thanks for the amazing work. I need some help understanding how to choose the layers for specific models, especially those without examples. I am currently looking at Qwen3-32b, which I see only ...

Abstract: Quantization has emerged as one of the most prevalent approaches to compress and accelerate neural networks. Recently, data-free quantization has been widely studied as a practical and ...

Running the example script llm-compressor/examples/quantization_w4a4_fp4/llama3_example.py results in a runtime error. Full traceback is included below.

The quantization of classical theories that admit more than one Hamiltonian description is considered. This is done from a geometrical viewpoint, both at the quantization level (geometric quantization ...