← Back to all news
arXiv Machine Learning By Kuanlin Chen, Chen-Wei Kuo, Cheng-En Ou

Global Ranks Survive, Selected Heads Shift: BOS-Sink Topology under 4-bit Weight-Only Quantization

Read the original on arXiv Machine Learning →

The paper investigates whether sink-aware attention head selection remains valid after 4‑bit NF4 weight‑only post‑training quantization. Using Sink Topology Consistency metrics, it finds that global rank preservation stays high across Qwen2.5 and Llama‑3.2 models, yet top‑k head overlap drops to 61–79% and layer‑specific sink‑mass shifts can be substantial. The study also shows that cross‑domain calibration degrades more than within‑domain precision and that recalibration with a small number of samples can recover most of the stability, though full‑map stability may require updating more layers.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv AI
Sep 3

Post-Training Ternarization of Qwen3-4B Capability, Effective Bit Budget, Storage Compression, and Deployment

The paper reports a post‑training ternarization of the 4‑billion‑parameter Qwen model, achieving an effective 1.641‑bit representation for 81.62 % of its weights while keeping activations at 16‑bit precision. Accuracy drops from 64.5 % to 54.7 % across ten capability tests, with uneven degradation (e.g., BoolQ 84.6 % of teacher performance, ARC‑Challenge 43.8 %). After packing the ternary planes, the model size shrinks from 8.29 GiB to 3.96 GiB with negligible change in perplexity, though inference speed is not improved.

By Anirudh Malik, M Sparsh Mehra, Poojith Devan
llmsefficiency
More like this →
arXiv AI
Sep 11

Scaling Post-Training Ternarisation to Qwen3-8B Capability Retention, Reproduction, Lossless Packing, and Packed Execution

The paper reports a large‑scale post‑training ternarisation of the Qwen3 language model, extending a conversion pipeline from the 4B to the 8B variant. Using KOTMS rotation, E2M‑ATQ adaptive ternarisation, and GPTQ‑style error compensation, the authors achieve a 1.361× perplexity ratio across three corpora and retain 78.5% of the FP16 accuracy on zero‑shot tasks, with the 8B model outperforming the 4B by 8.9 percentage points. The study also demonstrates lossless lattice‑aware packing, producing an 8.24 GiB checkpoint that preserves perplexity, and shows that direct packed execution can reach 15.52 tokens/s in 7.35 GiB, though packed GEMV remains slower than FP16 cuBLAS.

By Anirudh Malik, M Sparsh Mehra, Poojith Devan
llms
More like this →