Metraipolis › archive › dc_c8dd2e3128f7
SoloQ: Calibration-Free Quantization for Diffusion Language Models — arXiv:2610.07121
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.07121
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T11:40:52.729Z
- SHA-256 of the archived text
128f047b1b1e38f1ed58e4fd59ef2fd418c5fd7e3c9864de6e5bc2ff592b1a12- Stable URL of this page
https://metraipolis.com/documento/dc_c8dd2e3128f7
How to cite
SoloQ: Calibration-Free Quantization for Diffusion Language Models — arXiv:2610.07121 — arXiv (en), https://arxiv.org/abs/2610.07121 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c8dd2e3128f7 (Metraipolis archive dc_c8dd2e3128f7, sha256 128f047b1b1e38f1ed58e4fd59ef2fd418c5fd7e3c9864de6e5bc2ff592b1a12)
BibTeX
@misc{dcc8dd2e3128f7,
title = {SoloQ: Calibration-Free Quantization for Diffusion Language Models — arXiv:2610.07121},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.07121},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c8dd2e3128f7; sha256 128f047b1b1e38f1ed58e4fd59ef2fd418c5fd7e3c9864de6e5bc2ff592b1a12},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.07121. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Diffusion large language models dLLMs) have emerged as a promising alternative to autoregressive language models through bidirectional diffusion-based token generation. However, their growing model sizes and high inference costs make efficient deployment challenging: full-sequence denoising repeatedly invokes compute-intensive forward passes, while block-diffusion models additionally introduce a memory-intensive KV-cache. Low-bit weight-activation quantization is therefore attractive, yet existing dLLM post-training quantization methods rely on calibration data despite activation distributions shifting across masking states and denoising steps. We present SoloQ, a calibration-free quantization framework that maps weights and activations into a normalized rotated basis with a predictable marginal distribution, enabling data-independent quantization. SoloQ combines a structured K-RPBH rotation with a lightweight rescaling correction for calibration-free quantization. Its predictable post-rotation distribution supports both distribution-matched codebooks and hardware-native NVFP4. For block-diffusion models, SoloQ further applies commit-time KV-cache quantization to compress persistent states without perturbing the actively denoised block. Across full-sequence dLLMs (LLaDA and Dream) and block-diffusion dLLMs(Fast-dLLM v2 and Nemotron-Labs-Diffusion), SoloQ retains accuracy under 4-bit quantization and outperforms calibration-based baselines on knowledge- and reasoning-intensive benchmarks. With NVFP4, SoloQ reduces peak memory by up to 2.61X and accelerates end-to-end inference by up to 2.24X. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2610.07121 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-07T11:19:24.730Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).