arXiv:2608. 08081v1 Announce Type: cross Abstract: Large mixture-of-experts (MoE) language models with 26--120 billion parameters exceed the memory capacity of consumer devices through three simultaneous pressures: resident weight matrices, key-value (KV) cache state that grows linearly with context, and dozens of expert sublayers that must be paged on demand.
arXiv:2606. 03026v1 Announce Type: cross Abstract: Spiking language models expose activation sparsity that dense Transformer runtimes do not directly exploit.
Flash-dLLM is a training‑free inference acceleration framework that improves the speed and memory efficiency of Diffusion Large Language Models (dLLMs). It tackles GPU memory I/O bottlenecks by introducing an I/O‑aware fused KV‑cache kernel and then employs a draft‑and‑verify decoding strategy that uses the dLLM itself as both drafter and verifier. Experiments on mathematical reasoning and code‑generation tasks show Flash‑dLLM outperforms existing acceleration methods, achieving up to 11.0× speedups over the Elastic‑Cache baseline.
arXiv:2609.16338v1 Announce Type: new Abstract: Ternary Large Language Models (LLM) store every weight as one of three symbols $\{-1,0,+1\}$, so the cost of a ternary model is conventionally referenc...
The paper addresses the problem of non‑deterministic outputs from large language models (LLMs) when run on different GPU architectures, caused by floating‑point non‑associativity and hardware‑dependent kernel choices. It proposes a set of fixed‑configuration fused‑upcast GEMM kernels that load 16‑bit weights, upcast to FP32, and perform IEEE‑754 compliant reductions in a problem‑shape‑dependent order, ensuring identical linear‑layer outputs across NVIDIA Ampere, Ada, and Hopper GPUs. The new approach achieves 1.17–3.1× faster end‑to‑end performance than existing solutions and halves weight‑memory traffic while maintaining cross‑architecture reproducibility.
arXiv:2609.26333v1 Announce Type: new Abstract: Prefill and decode reward different approaches to quantization: low-precision arithmetic accelerates prompt processing, while compact weights reduce me...
arXiv:2608. 20210v1 Announce Type: cross Abstract: Small language models are usually built like large ones and then squeezed onto a CPU afterwards.
arXiv:2608. 01536v1 Announce Type: cross Abstract: Large Language Models (LLMs) increasingly rely on sparsity to reduce inference cost, but most prior work targets a single sparsity source-either weight or activation-and optimizes for batched multi-user inference.
arXiv:2607. 14568v1 Announce Type: cross Abstract: A companion study ran a 35B mixture-of-experts model on a 2011 NVIDIA Tesla C2075 (Fermi, sm_20, 6GB) as a GPU-prefill/CPU-decode hybrid, because the 4-bit model did not fit in device memory (arXiv:2606.
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.
DPS (Dual-Mode Precision LLM Serving) is a system that treats model‑weight memory as elastic by using a multi‑precision representation. Under normal load it serves the full‑accuracy model, but when KV‑cache pressure spikes it switches to a lower‑precision variant and reallocates unused weight memory for KV cache blocks. Built on Semi‑Unified Memory and implemented on top of vLLM, DPS boosts sustained throughput by 2.1–3.3× and effective pass@1 by up to +41 pp over static FP16 while maintaining FP16‑class accuracy.
Small language models are usually built like large ones and then squeezed onto a CPU afterwards. We did the opposite: we fixed the target first, one user, one token at a time, 4-bit weights, ordinary CPU, and chose the architecture to suit it.