arXiv:2607. 04244v1 Announce Type: new Abstract: This report describes our approach to the Efficient Qwen Competition, where the goal is to enable low-latency serving of Qwen3.
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...
SpecQuant is a training‑free framework that merges speculative decoding with multi‑parent quantization to enable adaptive, efficient inference of large language models. It generates several quantized variants (INT4, FP8, FP16) from a single base model and routes queries to the appropriate variant based on predicted complexity, using lightweight models for simple tasks and full‑precision models for complex reasoning. Evaluations on Qwen2.5 models across MMLU, AlpacaEval, and GSM8K show 35‑43% speedups with less than 2% accuracy loss, facilitating practical on‑device LLM deployment without specialized infrastructure.
arXiv:2608. 04048v1 Announce Type: cross Abstract: Serving large language models (LLMs) under diverse deployment constraints requires flexible trade-offs between accuracy, memory footprint, and throughput.
arXiv:2608.20953v1 Announce Type: cross Abstract: Serving large language models cheaply increasingly means shipping models that are both structurally compressed to a fraction of their parameters and...
arXiv:2608. 13966v1 Announce Type: new Abstract: As large language model inference shifts toward lower precision, post-training quantization (PTQ) becomes increasingly brittle, making quantization-aware training (QAT) essential for preserving model quality.
As large language model inference shifts toward lower precision, post-training quantization (PTQ) becomes increasingly brittle, making quantization-aware training (QAT) essential for preserving model...
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:2609.38166v1 Announce Type: cross Abstract: Recent LLMs increasingly adopt hybrid designs that replace standard attention with linear attention, such as Gated DeltaNet (GDN) and Kimi Delta Atte...
arXiv:2607. 24434v1 Announce Type: cross Abstract: Large Mixture-of-Experts (MoE) language models are attractive for end-device deployment because only a small subset of experts is active per token, but their routed expert weights often exceed accelerator memory.
arXiv:2607. 01831v1 Announce Type: cross Abstract: Long-context inference is increasingly common in large language model (LLM) serving, driven by retrieval-augmented generation and agentic systems.
arXiv:2606. 04238v1 Announce Type: cross Abstract: Aggressive weight quantization to 2-bit precision offers substantial throughput and memory gains for large language model (LLM) inference, but typically incurs severe accuracy degradation.
Large Mixture-of-Experts (MoE) language models are attractive for end-device deployment because only a small subset of experts is active per token, but their routed expert weights often exceed accelerator memory. We target latency-critical single-user settings where routed experts are staged on demand from CPU memory to a GPU or from Flash to a mobile NPU.