arXiv:2608.23816v1 Announce Type: new
Abstract: Quantized fine-tuning (QLoRA) saves memory but not time. It dequantizes every 4-bit weight on the fly, so it trains more slowly than fp16 LoRA. We pres...
By Md Romyull Islam
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
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
arXiv:2609.17109v1 Announce Type: new
Abstract: A common small-model deployment runs one shared backbone with several LoRA specialists that answer over the same context. Serving them naively re-prefi...
By Dushyant Rajput
arXiv:2608. 08910v1 Announce Type: cross Abstract: PTQTP decomposes LLM weight matrices into two ternary (trit) planes with two free per-group scales.
By Matteo Grella
The paper presents a 4‑bit quantization recipe, Minima: NVFP4 W4A4, that fully quantizes all linear layers—including the Gated DeltaNet (GDN) recurrent blocks—of the 27‑billion‑parameter Qwen3.8 LLM. Across a suite of benchmarks (perplexity, MMLU‑Pro, GSM8K, AIME'25, GPQA‑Diamond, LiveCodeBench, and RULER retrieval), the quantized model matches BF16 performance within seed noise while being 17.5 GiB in size and 14–19 % faster at prefill. The authors attribute this success to four mechanisms: block‑scaling of residuals, robust gate projections, the delta‑rule recurrence’s noise‑plateau behavior, and the per‑token quantization cost’s dilution over long contexts.
By Sergii Kozyrev, Davyd Maiboroda
arXiv:2609.39223v2 Announce Type: new
Abstract: Large language model (LLM) inference is increasingly moving toward lower precision to realize the throughput of hardware accelerators, but aggressive p...
By Weili Xu, Jisen Li, Yuqing Jian, Chenxi Li, Zhizhou Sha, Yifan Yu, Qingyang Wu, Chenfeng Xu, Zhongzhu Zhou, Tianyi Zhang, Ben Athiwaratkun
The paper introduces an error‑diffusion (ED) optimizer that replaces the full‑precision latent copy of binary‑weight language models with a small 2‑8‑bit residual buffer, reducing training state per weight from 97 bits to 3‑9 bits—up to 19× less. ED accumulates unrealized weight updates in the buffer and flips the binary weight when the accumulated value crosses a threshold aligned with the quantization grid, enabling efficient training on large transformers with minimal loss compared to latent‑weight baselines. The method scales to models with up to 19 M parameters on enwik8 and 70 M on wikitext‑103, maintaining performance within a few percent of reference while allowing on‑device adaptation within a 275 MB memory budget.
By Pierre-Olivier Bonin
A common small-model deployment runs one shared backbone with several LoRA specialists that answer over the same context. Serving them naively re-prefills that shared context once per specialist. We s...
The paper investigates how various non‑quantization factors—such as engine changes, server restarts, batching differences, and kernel selection—affect the performance of quantized language models compared to their BF16 baselines. Using 2,400 public decisions from Cloudflare’s Clef‑flash (9B) and Clef (27B) models on an NVIDIA GB10, the authors quantify the noise introduced by each factor and isolate the true impact of different quantization schemes (8‑bit, FP8, Q4_K_M, NVFP4). They find that non‑quantization sources contribute up to 0.92% of decision changes, while 4‑bit quantization can alter accuracy by up to 0.95 points, and they provide code, recipes, and detailed per‑record outputs for reproducibility.
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.
By Kuanlin Chen, Chen-Wei Kuo, Cheng-En Ou
arXiv:2610.19498v1 Announce Type: cross
Abstract: Model signing authenticates the full-precision weights W an LLM is released with, yet users run a quantized artifact Q whose producing transformation...
By Wei-Liang Liu, Cheng-Yen Tsai