GPTQ-intrinsic LoRA augments GPTQ with intrinsic low-rank compensation via Hessian modification to achieve layer-wise reconstruction bounds that match information-theoretic lower bounds under structural assumptions.
A comprehensive study on post-training quantization for large language models
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
TwinQuant learns quantization-friendly subspaces for 4-bit LLM weights via manifold optimization and a fused kernel, preserving near-FP16 accuracy with up to 1.8x speedup on LLaMA3 and Qwen3 models.
ProjQ constrains post-training quantization noise to a low-rank manifold through orthogonal subspace projection, enabling better compensation by LoRA adapters and preserving greater model plasticity than standard PTQ.
SplitQ improves low-bit PTQ for VLMs by isolating modality-specific outlier channels via MOCD and applying dual-branch adaptive calibration via ACC, outperforming prior methods on six datasets across W4A8 to W3A2 settings.
DECO is a sparse MoE architecture with ReLU-based routing, learnable expert scaling, and NormSiLU activation that matches dense Transformer performance at 20% expert activation and delivers 2.93x speedup on Jetson AGX Orin.
MCAP uses load-time Monte Carlo profiling to estimate layer importance, enabling dynamic quantization (W4A8 vs W4A16) and memory tiering (GPU/RAM/SSD) that delivers 1.5-1.8x higher decode throughput than llama-cpp Q4_0 on NVIDIA T4 while fitting models into previously infeasible memory budgets.
FrugalGPT learns query-specific cascades across heterogeneous LLM APIs to match or exceed top-model accuracy at far lower cost.
A per-layer, per-task bit-allocation rule based on hidden-activation entropy and variance reportedly matches full-precision TriviaQA accuracy within about one point — but the paper's tables and abstract are internally inconsistent.
The paper surveys techniques to speed up and reduce the resource needs of LLM inference, organized by data-level, model-level, and system-level changes, with comparative experiments on representative methods.
citing papers explorer
-
GPTQ-intrinsic LoRA: A Near-optimal Algorithm for Low-precision Quantization with Low-rank Adaptation
GPTQ-intrinsic LoRA augments GPTQ with intrinsic low-rank compensation via Hessian modification to achieve layer-wise reconstruction bounds that match information-theoretic lower bounds under structural assumptions.
-
TwinQuant: Learnable Subspace Decomposition for 4-Bit LLM Quantization
TwinQuant learns quantization-friendly subspaces for 4-bit LLM weights via manifold optimization and a fused kernel, preserving near-FP16 accuracy with up to 1.8x speedup on LLaMA3 and Qwen3 models.
-
ProjQ: Project-and-Quantize for Adapter-Aware LLM Compression
ProjQ constrains post-training quantization noise to a low-rank manifold through orthogonal subspace projection, enabling better compensation by LoRA adapters and preserving greater model plasticity than standard PTQ.
-
Breaking Modality Heterogeneity in Low-Bit Quantization for Large Vision-Language Models
SplitQ improves low-bit PTQ for VLMs by isolating modality-specific outlier channels via MOCD and applying dual-branch adaptive calibration via ACC, outperforming prior methods on six datasets across W4A8 to W3A2 settings.
-
DECO: Sparse Mixture-of-Experts with Dense-Comparable Performance on End-Side Devices
DECO is a sparse MoE architecture with ReLU-based routing, learnable expert scaling, and NormSiLU activation that matches dense Transformer performance at 20% expert activation and delivers 2.93x speedup on Jetson AGX Orin.
-
MCAP: Deployment-Time Layer Profiling for Memory-Constrained LLM Inference
MCAP uses load-time Monte Carlo profiling to estimate layer importance, enabling dynamic quantization (W4A8 vs W4A16) and memory tiering (GPU/RAM/SSD) that delivers 1.5-1.8x higher decode throughput than llama-cpp Q4_0 on NVIDIA T4 while fitting models into previously infeasible memory budgets.
-
FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance
FrugalGPT learns query-specific cascades across heterogeneous LLM APIs to match or exceed top-model accuracy at far lower cost.
-
You Had One Job: Per-Task Quantization Using LLMs' Hidden Representations
A per-layer, per-task bit-allocation rule based on hidden-activation entropy and variance reportedly matches full-precision TriviaQA accuracy within about one point — but the paper's tables and abstract are internally inconsistent.
-
A Survey on Efficient Inference for Large Language Models
The paper surveys techniques to speed up and reduce the resource needs of LLM inference, organized by data-level, model-level, and system-level changes, with comparative experiments on representative methods.