QuantVLA is the first post-training quantization framework for VLA models that quantizes the diffusion transformer action head and reports higher task success rates than full-precision baselines with roughly 70% memory savings on the quantized components.
hub
RPTQ: reorder-based post-training quantization for large language models
14 Pith papers cite this work. Polarity classification is still indexing.
14
Pith papers citing it
hub tools
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
SAB-LVLM proposes a significance-aware binarization technique for LVLMs that uses modality-guided Hessian-based maps to reweight binarization errors and improve performance under 1-bit constraints.
BITEMBED trains 1.58-bit ternary-weight LLM embedders with contrastive pre-training, supervised distillation, and multi-precision output training, matching FP16 teachers within ~0.6 MMTEB points at ~2x CPU speed.
OSAQ suppresses weight outliers in LLMs via a closed-form additive transformation from the Hessian's stable null space, improving 2-bit quantization perplexity by over 40% versus vanilla GPTQ with no inference overhead.
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.
DASH-Q uses a stable diagonal curvature estimate and weighted least squares to achieve robust ultra-low-bit post-training quantization of LLMs, improving zero-shot accuracy by 7% on average over baselines.
Redefining residual errors to include compensation-aware discrepancies and realigning calibration to full-precision outputs improves GPTQ and GPTAQ performance on LLMs.
AHCQ-SAM introduces ACNR, HLUQ, CAG, and LNQ quantization techniques that deliver 15.2% mAP gain on 4-bit SAM-B and 14.01% J&F gain on 4-bit SAM2-Tiny versus prior PTQ methods.
ASVD compresses LLMs by 10-30% and KV caches by 50% via activation-aware SVD that absorbs outliers into transformed weights and calibrates per-layer sensitivity.
On Ascend NPUs, OpenPangu-7B tolerates 4-bit weight quantization with minor accuracy loss, while OpenPangu-1B degrades sharply on math/code, and 2-bit/binary settings collapse to near-random output.
SEPTQ simplifies LLM post-training quantization to two steps via static global importance scoring and mask-guided column-wise weight updates, claiming superior results over baselines in low-bit settings.
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.
MixLLM uses global output-feature importance to set mixed bit-widths for LLM quantization and adds two-step dequantization plus software pipelining for system efficiency.
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
-
QuantVLA: Scale-Calibrated Post-Training Quantization for Vision-Language-Action Models
QuantVLA is the first post-training quantization framework for VLA models that quantizes the diffusion transformer action head and reports higher task success rates than full-precision baselines with roughly 70% memory savings on the quantized components.
-
SAB-LVLM: Significance-Aware Binarization for Large Vision-Language Models
SAB-LVLM proposes a significance-aware binarization technique for LVLMs that uses modality-guided Hessian-based maps to reweight binarization errors and improve performance under 1-bit constraints.
-
BitNet Text Embeddings
BITEMBED trains 1.58-bit ternary-weight LLM embedders with contrastive pre-training, supervised distillation, and multi-precision output training, matching FP16 teachers within ~0.6 MMTEB points at ~2x CPU speed.
-
OSAQ: Outlier Self-Absorption for Accurate Low-bit LLM Quantization
OSAQ suppresses weight outliers in LLMs via a closed-form additive transformation from the Hessian's stable null space, improving 2-bit quantization perplexity by over 40% versus vanilla GPTQ with no inference overhead.
-
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.
-
Robust Ultra Low-Bit Post-Training Quantization via Stable Diagonal Curvature Estimate
DASH-Q uses a stable diagonal curvature estimate and weighted least squares to achieve robust ultra-low-bit post-training quantization of LLMs, improving zero-shot accuracy by 7% on average over baselines.
-
Rethinking Residual Errors in Compensation-based LLM Quantization
Redefining residual errors to include compensation-aware discrepancies and realigning calibration to full-precision outputs improves GPTQ and GPTAQ performance on LLMs.
-
AHCQ-SAM: Toward Accurate and Hardware-Compatible Post-Training Segment Anything Model Quantization
AHCQ-SAM introduces ACNR, HLUQ, CAG, and LNQ quantization techniques that deliver 15.2% mAP gain on 4-bit SAM-B and 14.01% J&F gain on 4-bit SAM2-Tiny versus prior PTQ methods.
-
ASVD: Activation-aware Singular Value Decomposition for Compressing Large Language Models
ASVD compresses LLMs by 10-30% and KV caches by 50% via activation-aware SVD that absorbs outliers into transformed weights and calibrates per-layer sensitivity.
-
An Empirical Study of OpenPangu Quantization on Ascend NPUs
On Ascend NPUs, OpenPangu-7B tolerates 4-bit weight quantization with minor accuracy loss, while OpenPangu-1B degrades sharply on math/code, and 2-bit/binary settings collapse to near-random output.
-
SEPTQ: A Simple and Effective Post-Training Quantization Paradigm for Large Language Models
SEPTQ simplifies LLM post-training quantization to two steps via static global importance scoring and mask-guided column-wise weight updates, claiming superior results over baselines in low-bit settings.
-
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.
-
MixLLM: LLM Quantization with Global Mixed-precision between Output-features and Highly-efficient System Design
MixLLM uses global output-feature importance to set mixed bit-widths for LLM quantization and adds two-step dequantization plus software pipelining for system efficiency.
-
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.