ScaleSearch optimizes block floating point scales via fine-grained search to cut quantization error by 27% for NVFP4, improving PTQ by up to 15 points on MATH500 for Qwen3-8B and attention PPL by 0.77 on Llama 3.1 70B.
Quantization hurts reasoning? an empirical study on quantized reasoning models.arXiv preprint arXiv:2504.04823
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
citation-role summary
background 3
citation-polarity summary
verdicts
UNVERDICTED 8roles
background 3polarities
background 3representative citing papers
LAQuant improves long-decoding accuracy on quantized reasoning models like Qwen3-4B by 15pp on AIME25 via layer-wise lookahead loss, achieving 3.42x speedup over FP16.
QuantClaw dynamically routes precision in agent workflows to cut cost by up to 21.4% and latency by 15.7% while keeping or improving task performance.
LLM 2-bit quantization fails via either cumulative signal degradation or early computation collapse in key components.
FluxMoE decouples MoE expert weights from persistent GPU residency via on-demand paging, achieving up to 3x throughput gains over vLLM in memory-constrained inference without accuracy loss.
A pruning technique called Reasoning-Aware Compression (RAC) jointly reconstructs input and chain-of-thought activations to preserve reasoning performance better than standard methods when compressing models like DeepSeek-R1.
PubSwap uses a small public dataset for selective off-policy response swapping in federated RLVR to improve coordination and performance over standard baselines on math and medical reasoning tasks.
ZipMoE delivers up to 72.77% lower inference latency and 6.76x higher throughput for on-device MoE models via lossless compression and cache-affinity scheduling with a claimed provable guarantee.
citing papers explorer
-
ZipMoE: Efficient On-Device MoE Serving via Lossless Compression and Cache-Affinity Scheduling
ZipMoE delivers up to 72.77% lower inference latency and 6.76x higher throughput for on-device MoE models via lossless compression and cache-affinity scheduling with a claimed provable guarantee.