arXiv:2610. 01889v1 Announce Type: new Abstract: Should low-precision transformer inference use stochastic rounding (SR) or round-to-nearest (RN)?
arXiv:2606. 06521v1 Announce Type: cross Abstract: FP8 (E4M3) acceleration for attention computation offers significant throughput gains, but the 3-bit mantissa introduces precision challenges when the softmax probability matrix P is cast to FP8 before the P*V matrix multiplication.
The paper demonstrates that greedy decoding from large language models is not precision‑invariant: the same model, prompt, and decoding algorithm can produce different outputs when run in BF16 versus FP16 on identical hardware. Across six models (1.1B–7B parameters, four families, and 12B) and three benchmarks, 49–100 % of prompts diverge, with a single token flip often cascading into trajectory‑level divergence. The authors develop an empirical error‑propagation analysis that identifies the top‑two logit margin at the LM head as the key factor, and they propose a low‑overhead intervention—selective FP32 LM head recomputation—that improves exact agreement by 22–36 percentage points with less than 4 % latency overhead. "whyItMatters":"The findings reveal that precision choices can fundamentally alter model outputs, challenging the assumption of deterministic greedy decoding and highlighting the need for precision‑aware inference strategies."
arXiv:2606. 16620v1 Announce Type: cross Abstract: Inference-time scaling has become the dominant lever for improving language-model reasoning, but existing methods derive rollout diversity from a single source: stochastic token-level sampling.
arXiv:2607. 09800v1 Announce Type: new Abstract: Training in reduced floating-point precision can silently halt learning: when a gradient-descent weight update falls below half the unit in the last place (ULP) of the weight, it rounds away and that coordinate freezes while its gradient is still nonzero.
The paper surveys the use of linear, function‑preserving transforms in 4‑bit large‑language‑model (LLM) quantization, formalizing the underlying principle as the "Great Inversion"—the trade‑off between energy concentration favored by allocation‑flexible coding and within‑group flattening favored by grouped shared‑scale quantization. It reviews 200 works, classifies 43 transform methods by structure, data‑awareness, construction approach, and runtime cost, and examines how they interact with GPTQ rounding. The study also explores how different number formats (FP4, MXFP4, NVFP4) influence the optimal transform choice and outlines open research problems. "whyItMatters":"The survey clarifies the conflicting objectives in transform‑based LLM quantization and provides a practical guide for selecting transforms based on deployment regime, thereby informing future research and deployment strategies."
arXiv:2607. 08779v1 Announce Type: cross Abstract: The signed integer alphabet contains one more negative representable value than positive.
arXiv:2606. 18463v1 Announce Type: cross Abstract: Distributed stochastic gradient descent (SGD) is limited by communication rather than computation, since each iteration requires an AllReduce across processes.
arXiv:2510. 04212v4 Announce Type: replace-cross Abstract: The pursuit of computational efficiency has driven the adoption of low-precision formats for training transformer models.
arXiv:2609.21058v1 Announce Type: cross Abstract: Language models can now write GPU kernels that outperform PyTorch. We evaluate five model configurations on KernelBench level 1 and find that a front...
arXiv:2607. 02893v1 Announce Type: new Abstract: Low-bit quantization shrinks language models but treats precision as a single global hyper-parameter: every weight uses the same bit-width.
The study investigates how post‑training quantization (PTQ) affects proactive interference (PI) in large language models. Using bitsandbytes, the authors compare FP16, INT8, and INT4/NF4 precision across three instruction‑tuned models and find that INT4 quantization markedly degrades accuracy under high interference, with INT8 also incurring a smaller penalty in two of the three models. The degradation is linked to increased same‑key intrusion errors and originates in the quantized transformer backbone rather than the output layer.
arXiv:2605. 06675v2 Announce Type: replace Abstract: Large language models cache all previously computed key-value (KV) pairs during generation, and this KV cache grows linearly with sequence length, making it a primary memory bottleneck for serving.