quantize
Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record.
quantize appears in the code Syntology harvested for 70 papers, as 36 distinct code bodies found in 71 places (a place is one code body under one paper). Of the 70 papers, 62 with a sample that ran: 27 with a run with no instrument failure, 35 where every run was a failure of Syntology's instrument. 16 of the code bodies carry a behaviour fingerprint.
What this page is not. Routines are grouped here by the exact string of their function or class name. Nothing asserts that two samples named quantize do the same thing, share code, or are comparable; the name is a string, not an identity. Behaviour outputs (what a fingerprinted sample returned on the shared battery) are not in this export and are not shown here; get_code(code_sha256="…") returns this sample's fingerprint on the shared battery, with the battery's shuffled null and lift; not shown on this site (how to connect). "Ran" means executed on a synthesized fixture, not that the code is correct or reproduces a paper.
Samples Syntology
The 36 distinct code bodies named quantize: 29 ran (of which 1 constructed an object rather than computing a result; 19 with no instrument failure: 2 honoured, 0 violated, 17 with no contract checked; 10 where Syntology's instrument failed) · 7 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. One tile per status, in the site's fixed vocabulary, each code body counted once:
Licence is a property of each copy, so it is counted per place: 37 of the 71 places are pointer only (Syntology does not serve that copy's text); at 15 of those this paper's copy is under a permissive licence, but the stored copy of the same code that Syntology serves is not cleared for its text (hover the licence cell for why). This site shows no code text for any sample; every row below links to the file in its repository where the record names one.
“Ran” means the sample executed on a synthesized input; it does not mean the output is correct. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “the contract check could not run” (RAISES, DEP_MISSING or TIMEOUT; hover a row's label for which) are failures of Syntology's instrument, not of the code, and those samples did run. The ran count above is every status except unverified, the same rule as each paper page; “with no instrument failure” is honoured, violated and ran with no contract checked. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.
Papers
70 papers shown of 70, newest first; 71 places in the table. A paper with no recorded date is placed by the month its arXiv id encodes, shown in the Date column as YYYY-MM (from id). One row per place: a paper whose repository defines the name more than once appears more than once, and the same code body held for several papers appears once under each, with the same status. Titles and dates are the archive's archive 2025-07-28 for papers in the archive, and the graph's for 5 papers added by Syntology; 5 papers have no page here and are shown by their id only (arXiv: for an arXiv id; an id from another venue, such as ACL Anthology or AAAI, is named as that venue's id, never as an arXiv id). Status and fingerprint are Syntology's record of each code body; licence is recorded for each place. The File cell ends with the code body's code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.
| Paper | Date | File | Status Syntology | Licence |
|---|---|---|---|---|
| LongSpike: Fractional Order Spiking State Space Models for Efficient Long Sequence Learning added by Syntology | 2026-06 (from id) | xinruihe389-commits/LongSpike/src/dataloaders/audio.py 1631cd936e9b1a90 |
ran; the contract check could not run (RAISES) | licence not identified · pointer only |
| FASQ: Flexible Accelerated Subspace Quantization for Calibration-Free LLM Compression added by Syntology | 2026-05 (from id) | ist-daslab/gptq/quant.py 41c57e55d21c4d96 |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant | Apache-2.0 (permissive) |
| AIRE-Prune: Asymptotic Impulse-Response Energy for State Pruning in State Space Models added by Syntology | 2026-02 (from id) | falcon-arrow/AIRE-Prune/s5/dataloaders/audio.py 1631cd936e9b1a90 |
ran; the contract check could not run (RAISES) | Apache-2.0 (permissive) here; the stored copy is pointer only |
| Towards Understanding Best Practices for Quantization of Vision-Language Models added by Syntology | 2026-01 (from id) | gautomdas/mmq/gptq_blip2.py 41c57e55d21c4d96 |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant | no licence file found · pointer only |
| AnyBCQ: Hardware Efficient Flexible Binary-Coded Quantization for Multi-Precision LLMs added by Syntology | 2025-10 (from id) | naver-aics/anybcq/anybcq/quantization/anybcq.py 121de7b5e46dc9b5 |
unverified | Apache-2.0 (permissive) |
| Layer-Adaptive State Pruning for Deep State Space Models | 5 Nov 2024 | msgwak/LAST/s5/dataloaders/audio.py 1631cd936e9b1a90 |
ran; the contract check could not run (RAISES) | no licence file found · pointer only |
| Residual vector quantization for KV cache compression in large language model | 21 Oct 2024 | iankur/vqllm/vqllm/quantizer/utils.py af4e407a59eea9ab |
ran | MIT (permissive) |
| SLiM: One-shot Quantization and Sparsity with Low-rank Approximation for LLM Weight Compression | 12 Oct 2024 | mohammad-mozaffari/slim/slim/sparsegpt.py 50ceff9d34d96d60 |
ran | MIT (permissive) |
| LeanQuant: Accurate Large Language Model Quantization with Loss-Error-Aware Grid | 14 Jul 2024 | LeanModels/LeanQuant/quant.py 41c57e55d21c4d96 |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant | no licence file found · pointer only |
| AdaZeta: Adaptive Zeroth-Order Tensor-Train Adaption for Memory-Efficient Large Language Models Fine-Tuning | 26 Jun 2024 | yifanycc/adazeta/large_models/loretta/tuners/loretta_adp.py e52c09d7918640f3 |
ran | GPL-3.0 (copyleft) · pointer only |
| Attention-aware Post-training Quantization without Backpropagation | 19 Jun 2024 | SamsungLabs/BoA/quantizers/boa.py b6a41484b3b9b656 |
ran · our draft was wrong | licence not identified · pointer only |
| Examining Post-Training Quantization for Mixture-of-Experts: A Benchmark | 12 Jun 2024 | unites-lab/moe-quantization/auto_gptq/quantization/quantizer.py 41c57e55d21c4d96 |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant | MIT (permissive) |
| P-SpikeSSM: Harnessing Probabilistic Spiking State Space Models for Long-Range Dependency Tasks | 5 Jun 2024 | NeuroCompLab-psu/PSpikeSSMs/src/dataloaders/audio.py 1631cd936e9b1a90 |
ran; the contract check could not run (RAISES) | MIT (permissive) here; the stored copy is pointer only |
| MagR: Weight Magnitude Reduction for Enhancing Post-Training Quantization | 2 Jun 2024 | AozhongZhang/MagR/quant.py 41c57e55d21c4d96 |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant | MIT (permissive) |
| Sparse Expansion and Neuronal Disentanglement | 24 May 2024 | shavit-lab/sparse-expansion/utils/quant.py 50ceff9d34d96d60 |
ran | MIT (permissive) |
| FrameQuant: Flexible Low-Bit Quantization for Transformers | 10 Mar 2024 | vsingh-group/framequant/quant.py ff8ffe5499b035fb |
ran | no licence file found · pointer only |
| NiteDR: Nighttime Image De-Raining with Cross-View Sensor Cooperative Learning for Dynamic Driving Scenes | 28 Feb 2024 | cidanshi/nitedr-nighttime-image-de-raining/utils_image.py b1c1acd3c89a39f3 |
ran · our draft was wrong fingerprinted | no licence file found · pointer only |
| SparseLLM: Towards Global Pruning for Pre-trained Language Models | 28 Feb 2024 | BaiTheBest/SparseLLM/quant.py 50ceff9d34d96d60 |
ran | Apache-2.0 (permissive) |
| Adaptive Convolutional Neural Network for Image Super-resolution | 24 Feb 2024 | hellloxiaotian/adsrnet/HDSRNet/utility.py b1c1acd3c89a39f3 |
ran · our draft was wrong fingerprinted | no licence file found · pointer only |
| State Space Models for Event Cameras | 23 Feb 2024 | lindermanlab/S5/s5/dataloaders/audio.py 1631cd936e9b1a90 |
ran; the contract check could not run (RAISES) | MIT (permissive) here; the stored copy is pointer only |
| ASVD: Activation-aware Singular Value Decomposition for Compressing Large Language Models | 10 Dec 2023 | hahnyuan/asvd4llm/quantization.py 41c57e55d21c4d96 |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant | MIT (permissive) |
| DeltaZip: Efficient Serving of Multiple Full-Model-Tuned LLMs | 8 Dec 2023 | eth-easl/deltazip/deltazip/core/quant.py 8f8eedd720c09255 |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant | Apache-2.0 (permissive) |
| In-Context Learning for MIMO Equalization Using Transformer-Based Sequence Models | 10 Nov 2023 | kclip/icl-equalization/EQ_data.py 7d88083dd6876883 |
ran | no licence file found · pointer only |
| $Λ$-Split: A Privacy-Preserving Split Computing Framework for Cloud-Powered Generative AI | 23 Oct 2023 | nishio-laboratory/lambda_split/preliminary/text_to_image_base.py dabcd15634e546ca |
ran fingerprinted | MIT (permissive) |
| Never Train from Scratch: Fair Comparison of Long-Sequence Models Requires Data-Driven Priors | 4 Oct 2023 | idoamos/not-from-scratch/src/dataloaders/audio.py 1631cd936e9b1a90 |
ran; the contract check could not run (RAISES) | MIT (permissive) here; the stored copy is pointer only |
| PB-LLM: Partially Binarized Large Language Models | 29 Sep 2023 | hahnyuan/binaryllm/gptq_pb/high_quant.py 50ceff9d34d96d60 |
ran | MIT (permissive) |
| Differentiable JPEG: The Devil is in the Details | 13 Sep 2023 | necla-ml/diff-jpeg/diff_jpeg/encode.py 544144a7ead4418d |
unverified | BSD-3-Clause (permissive) |
| Toward Sufficient Spatial-Frequency Interaction for Gradient-aware Underwater Image Enhancement | 8 Sep 2023 | zhihefang/SFGNet/utils.py b1c1acd3c89a39f3 |
ran · our draft was wrong fingerprinted | no licence file found · pointer only |
| ChatHome: Development and Evaluation of a Domain-Specific Language Model for Home Renovation | 28 Jul 2023 | lianjiatech/belle/models/gptq/quant.py 50ceff9d34d96d60 |
ran | Apache-2.0 (permissive) |
| OWQ: Outlier-Aware Weight Quantization for Efficient Fine-Tuning and Inference of Large Language Models | 4 Jun 2023 | xvyaward/qeft/qeft/quant.py a166c4b79b21b60a |
ran · our draft was wrong fingerprinted | MIT (permissive) |
| AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration | 1 Jun 2023 | identical code first harvested elsewhere a166c4b79b21b60a |
ran · our draft was wrong fingerprinted | licence of this copy not recorded |
| QLoRA: Efficient Finetuning of Quantized LLMs | 23 May 2023 | shuxueslpi/chatGLM-6B-QLoRA/merge_lora_and_quantize.py 9b9c46fa571c5690 |
ran · our draft was wrong | no licence file found · pointer only |
| Learning Semantic-Aware Knowledge Guidance for Low-Light Image Enhancement | 14 Apr 2023 | langmanbusi/semantic-aware-low-light-image-enhancement/DRBN_SKF/src/utility.py b1c1acd3c89a39f3 |
ran · our draft was wrong fingerprinted | MIT (permissive) here; the stored copy is pointer only |
| Vector Quantized Time Series Generation with a Bidirectional Prior Model | 8 Mar 2023 | ml4its/timevqvae/src/timevqvae/utils/nn.py e323b33b21b740e9 |
ran | MIT (permissive) |
| ViTALiTy: Unifying Low-rank and Sparse Approximation for Vision Transformer Acceleration with a Linear Taylor Attention | 9 Nov 2022 | GATECH-EIC/ViTaLiTy/src/quantize.py 3f1de05d36b1a783 |
ran | Apache-2.0 recorded; this copy not marked cleared · pointer only |
| Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned | 23 Aug 2022 | lyqcom/red30/metrics.py aa9d5683a00262dc |
ran fingerprinted | Apache-2.0 (permissive) |
| Simplified State Space Layers for Sequence Modeling | 9 Aug 2022 | leonty1/deepldnn/src/dataloaders/audio.py 1631cd936e9b1a90 |
ran; the contract check could not run (RAISES) | Apache-2.0 (permissive) here; the stored copy is pointer only |
| Optimal Clipping and Magnitude-aware Differentiation for Improved Quantization-aware Training | 13 Jun 2022 | zavareh1/ClippedQuantFL/model/cifar10DET_quantizedmaxscalar.py 00cb1200d5219763 |
ran fingerprinted | MIT (permissive) |
| UViM: A Unified Modeling Approach for Vision with Learned Guiding Codes | 20 May 2022 | google-research/big_vision/big_vision/models/proj/uvim/vit.py 0abb725ab0e6cfb6 |
unverified | Apache-2.0 (permissive) |
| Missing Data Imputation and Acquisition with Deep Hierarchical Models and Hamiltonian Monte Carlo | 9 Feb 2022 | ipeis/HH-VAEM/src/mutual_information.py 6ad9b288c102f26a |
ran fingerprinted | MIT (permissive) |
| Unsupervised Degradation Representation Learning for Blind Super-Resolution | 1 Apr 2021 | LongguangWang/DASR/utility.py b1c1acd3c89a39f3 |
ran · our draft was wrong fingerprinted | MIT (permissive) here; the stored copy is pointer only |
| Hierarchical Autoregressive Modeling for Neural Video Compression | 19 Oct 2020 | buggyyang/hier-video-compression/models.py 771654b864892612 |
ran; the contract check could not run (RAISES) | no licence file found · pointer only |
| Invertible Image Rescaling | 12 May 2020 | andreasfloros/IRN/utils.py 852a7c9de098c70e |
ran fingerprinted | MIT (permissive) |
| Learning A Single Network for Scale-Arbitrary Super-Resolution | 8 Apr 2020 | LongguangWang/ArbSR/utility.py b1c1acd3c89a39f3 |
ran · our draft was wrong fingerprinted | MIT (permissive) here; the stored copy is pointer only |
| Closed-loop Matters: Dual Regression Networks for Single Image Super-Resolution | 16 Mar 2020 | guoyongcs/DRN/utility.py b1c1acd3c89a39f3 |
ran · our draft was wrong fingerprinted | MIT (permissive) here; the stored copy is pointer only |
| Zooming Slow-Mo: Fast and Accurate One-Stage Space-Time Video Super-Resolution | 26 Feb 2020 | YapengTian/TDAN-VSR-CVPR-2020/solver.py 91df9c98a6149376 |
ran fingerprinted | MIT (permissive) |
| Private Summation in the Multi-Message Shuffle Model | 2020-02 (from id) | adriagascon/shuffledpsummation/real_sum_estimator.py c7d57ba9a9e79cf4 |
unverified | no licence file found · pointer only |
| Post-Training Piecewise Linear Quantization for Deep Neural Networks | 31 Jan 2020 | jakc4103/piecewise-quantization/utils/quantize.py ce590a0abac42625 |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted | no licence file found · pointer only |
| Fractional Skipping: Towards Finer-Grained Dynamic CNN Inference | 3 Jan 2020 | Torment123/DFS/models.py 7d546c0310d1c591 |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted | no licence file found · pointer only |
| Deformable Non-local Network for Video Super-Resolution | 24 Sep 2019 | wh1h/DNLN/src/utility.py b1c1acd3c89a39f3 |
ran · our draft was wrong fingerprinted | MIT (permissive) here; the stored copy is pointer only |
| Deformable Non-local Network for Video Super-Resolution | 24 Sep 2019 | wh1h/DNLN/src/trainer.py 91df9c98a6149376 |
ran fingerprinted | MIT (permissive) |
| Robust Invisible Video Watermarking with Attention | 3 Sep 2019 | DAI-Lab/RivaGAN/rivagan/rivagan.py 34dad53061b916d4 |
ran · honoured contract fingerprinted | MIT (permissive) |
| Densely Residual Laplacian Super-Resolution | 28 Jun 2019 | saeed-anwar/DRLN/TestCode/code/utility.py b1c1acd3c89a39f3 |
ran · our draft was wrong fingerprinted | MIT (permissive) here; the stored copy is pointer only |
| Sparsified SGD with Memory | 20 Sep 2018 | epfml/sparsifiedSGD/qsgd.py 96442fc743ff7faf |
ran fingerprinted | Apache-2.0 (permissive) |
| Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separation | 20 Sep 2018 | IliasDG/Demucs_Project/quantize.py 95678855edc371ba |
ran fingerprinted | MIT recorded; this copy not marked cleared · pointer only |
| Neural Ordinary Differential Equations | 19 Jun 2018 | HolmesShuan/OISR-PyTorch/NTIRE2019/OISR/src/utility.py b1c1acd3c89a39f3 |
ran · our draft was wrong fingerprinted | BSD-2-Clause (permissive) here; the stored copy is pointer only |
| RedNet: Residual Encoder-Decoder Network for indoor RGB-D Semantic Segmentation | 4 Jun 2018 | lyqcom/rednet30/Initial/metrics.py aa9d5683a00262dc |
ran fingerprinted | Apache-2.0 (permissive) |
| Maintaining Natural Image Statistics with the Contextual Loss | 13 Mar 2018 | subeeshvasu/2018_subeesh_epsr_eccvw/EPSR_testcode/code/utility.py b1c1acd3c89a39f3 |
ran · our draft was wrong fingerprinted | MIT (permissive) here; the stored copy is pointer only |
| Deep Back-Projection Networks For Super-Resolution | 7 Mar 2018 | LEEPEIQIN/EDSR/src/utility.py b1c1acd3c89a39f3 |
ran · our draft was wrong fingerprinted | MIT (permissive) here; the stored copy is pointer only |
| signSGD: Compressed Optimisation for Non-Convex Problems | 13 Feb 2018 | identical code first harvested elsewhere 8c0c528956fb38b9 |
unverified | licence of this copy not recorded |
| Attacking Binarized Neural Networks | 1 Nov 2017 | AngusG/cleverhans-attacking-bnns/cleverhans_tutorials/resnet_model.py fb9a05da9fb0eb6e |
unverified | MIT recorded; this copy not marked cleared · pointer only |
| Trained Ternary Quantization | 4 Dec 2016 | vinsis/ternary-quantization/quantification.py d68f2c13b2387a62 |
ran · honoured contract fingerprinted | MIT (permissive) |
| QSGD: Communication-Efficient SGD via Gradient Quantization and Encoding | 7 Oct 2016 | scottjiao/Gradient-Compression-Methods/utils.py 8c0c528956fb38b9 |
unverified | no licence file found · pointer only |
| Neural NILM: Deep Neural Networks Applied to Energy Disaggregation | 23 Jul 2015 | JackKelly/neuralnilm_prototype/neuralnilm/source.py a4c12d1effb52c55 |
unverified | MIT (permissive) |
| Going Deeper with Convolutions | 17 Sep 2014 | HolmesShuan/AIM2020-RealSR/src/utility.py 7185b10fd4807808 |
ran fingerprinted | BSD-2-Clause (permissive) |
| Intriguing properties of neural networks | 21 Dec 2013 | anishathalye/neural-hash-collider/collide.py 9e4646f8887baf9a |
ran fingerprinted | MIT (permissive) |
| OpenReview id openreview_d3RFDLBw01 | AI2C-Lab/STLA/quantizer.py 41c57e55d21c4d96 |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant | Apache-2.0 (permissive) | |
| CVF open access id Deng_LAU-Net_Latitude_Adaptive_Upscaling_Network_for_Omnidirectional_Image_Super-Resolution_CVPR_2021_paper | wangh-allen/LAU-Net/utility.py b1c1acd3c89a39f3 |
ran · our draft was wrong fingerprinted | Apache-2.0 (permissive) here; the stored copy is pointer only | |
| ACL Anthology id 2025.findings-emnlp.1054 | IST-DASLab/sparsegpt/quant.py 50ceff9d34d96d60 |
ran | Apache-2.0 (permissive) | |
| ACL Anthology id 2024.findings-naacl.145 | LianjiaTech/BELLE/models/gptq/quant.py 50ceff9d34d96d60 |
ran | Apache-2.0 (permissive) | |
| ACL Anthology id 2023.emnlp-main.892 | SamsungLabs/Z-Fold/quant.py 41c57e55d21c4d96 |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant | MIT (permissive) |
This site shows no code text; each File cell links to the file on GitHub at the repository's current default branch, which may have changed since the harvest. "Pointer only" means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is under a permissive licence, but the stored copy of the same code that Syntology serves is not cleared for its text. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence cell for the reason. Per-sample records for a paper are on its paper page under "Code Syntology ran".
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections