SliM-LLM: Salience-Driven Mixed-Precision Quantization for Large Language Models
Reviewed by Pithpith:JWYK2M2Lopen to challenge →
read the original abstract
Post-training quantization (PTQ) is an effective technique for compressing large language models (LLMs). However, while uniform-precision quantization is computationally efficient, it often compromises model performance. To address this, we propose SliM-LLM, a salience-driven mixed-precision quantization framework that allocates bit-widths at the group-wise. Our approach leverages the observation that important weights follow a structured distribution and introduces two key components: \textbf{1)} \textit{Salience-Determined Bit Allocation} adaptively assigns bit-widths to groups within each layer based on their salience; and \textbf{2)} \textit{Salience-Weighted Quantizer Calibration} optimizes quantizer parameters by incorporating element-level salience. With its structured partitioning, SliM-LLM provides a hardware-friendly solution that matches the efficiency of uniform quantization methods while improving accuracy. Experiments show that SliM-LLM achieves superior performance across various LLMs at low bit-widths. For example, a 2-bit quantized LLaMA-7B model reduces memory usage by nearly 6x compared to the floating-point baseline, decreases perplexity by 48\% compared to state-of-the-art gradient-free PTQ methods, and maintains GPU inference speed. Additionally, the extended version, SliM-LLM$^+$, which incorporates gradient-based quantization, further reduces perplexity by 35.1\%. Our code is available at https://github.com/Aaronhuang-778/SliM-LLM
This paper has not been read by Pith yet.
Forward citations
Cited by 8 Pith papers
-
LoopQ: Quantization for Recursive Transformers
LoopQ provides a loop-aware PTQ framework for recursive Transformers that mitigates distribution shift, state reuse, and recursive error accumulation, yielding 68.8% higher average accuracy and 87.7% lower perplexity ...
-
SpinQuant: LLM quantization with learned rotations
SpinQuant learns optimal rotations to enable accurate 4-bit quantization of LLM weights, activations, and KV cache, reducing the zero-shot gap to full precision to 2.9 points on LLaMA-2 7B.
-
GRINQH: Graded Input-based Quantization Hierarchy for Efficient LLM Generation
GRINQH introduces a graded input-based quantization hierarchy that dynamically assigns multi-precision weights using activation magnitudes as importance proxy, unifying quantization with sparsification to improve LLM ...
-
ActQuant: Sub-4-bit Action-Guided Quantization for Vision-Language-Action Models
ActQuant achieves sub-4-bit (down to 2.5 bpw) quantization of VLA models via action-contribution bit allocation and curvature-based scale tuning, retaining over 90% performance on LIBERO and physical robot tasks.
-
LBLLM: Lightweight Binarization of Large Language Models via Three-Stage Distillation
LBLLM achieves better accuracy than prior binarization methods for LLMs by decoupling weight and activation quantization through initialization, layer-wise distillation, and learnable activation scaling.
-
When Attention Sink Emerges in Language Models: An Empirical View
Attention sinks emerge in language models from softmax-induced token dependence on attention scores and do not appear when using sigmoid attention without normalization in models up to 1B parameters.
-
Prune, Update and Trim: Robust Structured Pruning for Large Language Models
Putri is a structured pruning technique for LLMs that compensates for pruning errors via weight updates and sequential processing while pruning at the attention-head level to reach state-of-the-art results at extreme ...
-
Attention Sink Forges Native MoE in Attention Layers: Sink-Aware Training to Address Head Collapse
Attention sinks forge native MoE mechanisms in attention layers that cause head collapse, addressed by sink-aware training with auxiliary load balancing.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.