REVIEW 10 cited by
ZeroQuant: Efficient and Affordable Post-Training Quantization for Large-Scale Transformers
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
ZeroQuant: Efficient and Affordable Post-Training Quantization for Large-Scale Transformers
read the original abstract
How to efficiently serve ever-larger trained natural language models in practice has become exceptionally challenging even for powerful cloud servers due to their prohibitive memory/computation requirements. In this work, we present an efficient and affordable post-training quantization approach to compress large Transformer-based models, termed as ZeroQuant. ZeroQuant is an end-to-end quantization and inference pipeline with three main components: (1) a fine-grained hardware-friendly quantization scheme for both weight and activations; (2) a novel affordable layer-by-layer knowledge distillation algorithm (LKD) even without the access to the original training data; (3) a highly-optimized quantization system backend support to remove the quantization/dequantization overhead. As such, we are able to show that: (1) ZeroQuant can reduce the precision for weights and activations to INT8 in a cost-free way for both BERT and GPT3-style models with minimal accuracy impact, which leads to up to 5.19x/4.16x speedup on those models compared to FP16 inference; (2) ZeroQuant plus LKD affordably quantize the weights in the fully-connected module to INT4 along with INT8 weights in the attention module and INT8 activations, resulting in 3x memory footprint reduction compared to the FP16 model; (3) ZeroQuant can be directly applied to two of the largest open-sourced language models, including GPT-J6B and GPT-NeoX20, for which our INT8 model achieves similar accuracy as the FP16 model but achieves up to 5.2x better efficiency.
Forward citations
Cited by 10 Pith papers
-
Alignment Collapse Under KV Cache Quantization: Diagnosis and Mitigation
KV cache quantization silently erodes LLM safety alignment via vulnerable low-dimensional subspaces, diagnosed by Per-Channel Reduction into three failure modes and mitigated training-free with up to 97% recovery.
-
QLoRA: Efficient Finetuning of Quantized LLMs
QLoRA finetunes 4-bit quantized LLMs via LoRA adapters to match full-precision performance while using far less memory, enabling 65B-scale training on single GPUs and producing Guanaco models near ChatGPT level.
-
Accelerating Large Language Model Decoding with Speculative Sampling
Speculative sampling accelerates LLM decoding 2-2.5x by letting a draft model propose short sequences that the target model scores in parallel, then applies modified rejection sampling to keep the exact target distribution.
-
GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers
GPTQ quantizes 175B-parameter GPT models to 3-4 bits per weight in one shot using approximate second-order information, achieving negligible accuracy degradation and 3-4x inference speedups.
-
LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale
LLM.int8() performs 8-bit inference for transformers up to 175B parameters with no accuracy loss by combining vector-wise quantization for most features with 16-bit mixed-precision handling of systematic outlier dimensions.
-
Motion-Compensated Weight Compression
MCWC aligns permutation-symmetric blocks across layers to enable sequential prediction and residual entropy coding, improving rate-accuracy tradeoffs versus quantization and prior codecs on language and vision models.
-
Diagnostic-Driven Layer-Wise Compensation for Post-Training Quantization of Encoder-Decoder ASR Models
FADE adaptively compensates for quantization errors layer-by-layer in ASR models using diagnostic scores from weight geometry and calibration data, yielding lower word error rates at 3- and 4-bit precision.
-
H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models
H2O evicts non-heavy-hitter tokens from the KV cache using a dynamic submodular policy, retaining recent and frequent-co-occurrence tokens to reduce memory while preserving accuracy.
-
AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration
AWQ quantizes LLM weights to low bits by scaling salient channels based on activation statistics, outperforming prior methods on language, coding, math, and multi-modal benchmarks.
-
A KL Lens on Quantization: Fast, Forward-Only Sensitivity for Mixed-Precision SSM-Transformer Models
KL divergence provides a superior forward-only metric for identifying quantization-sensitive parts in SSM-Transformer hybrids, outperforming MSE and SQNR and supporting practical mixed-precision deployment on edge devices.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.