| Garbage Attention in Large Language Models: <BOS> Sink Heads and Sink-aware Pruning added by Syntology |
2026-01 (from id) |
CASIA-LMC-Lab/FLAP/lib/prune.py 6ccf0fe3fd4574d5 |
unverified |
Apache-2.0 (permissive) |
| PuzzleMoE: Efficient Compression of Large Mixture-of-Experts Models via Fine-Grained Expert Merging and Bit-packed Inference added by Syntology |
2025-11 (from id) |
Supercomputing-System-AI-Lab/PuzzleMoE/puzzlemoe/utils/merge_experts_function.py 60d24b07d3b90b7c |
unverified |
Apache-2.0 (permissive) |
| arXiv:2507.23279 |
2025-07 (from id) |
ZunhaiSu/Super-Experts-Profilling/data_utils.py 709a6f261dbed787 |
unverified |
no licence file found · pointer only |
| arXiv:2506.09351 |
2025-06 (from id) |
yuchenblah/DIVE/prune/lib/calidata_random.py 92ee6796edcd33e1 |
unverified |
Apache-2.0 (permissive) |
| arXiv:2506.09351 |
2025-06 (from id) |
yuchenblah/DIVE/prune/lib/calidata_select_8.py fe56cd1859314741 |
unverified |
Apache-2.0 (permissive) |
| SAFE: Finding Sparse and Flat Minima to Improve Pruning |
7 Jun 2025 |
LOG-postech/safe-torch/language/lib/prune.py d53a6dae4f8104ea |
unverified |
MIT (permissive) |
| DLP: Dynamic Layerwise Pruning in Large Language Models |
27 May 2025 |
ironartisan/dlp/lib/prune.py c668683d68ff5099 |
unverified |
Apache-2.0 (permissive) |
| AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment |
15 Nov 2024 |
GATECH-EIC/AmoebaLLM/width_shrink/data.py 7630a157a3b32ab9 |
unverified |
MIT (permissive) |
| WAGLE: Strategic Weight Attribution for Effective and Modular Unlearning in Large Language Models |
23 Oct 2024 |
OPTML-Group/WAGLE/src/dataset/dataset.py 7630a157a3b32ab9 |
unverified |
MIT (permissive) |
| Quamba: A Post-Training Quantization Recipe for Selective State Space Models |
17 Oct 2024 |
enyac-group/quamba/quamba/data_loaders.py eb9d2957b3161128 |
ran
|
licence not identified · pointer only |
| SLiM: One-shot Quantization and Sparsity with Low-rank Approximation for LLM Weight Compression |
12 Oct 2024 |
mohammad-mozaffari/slim/slim/data.py ddc3bcb5e5b4ab8d |
unverified |
MIT (permissive) |
| MaskLLM: Learnable Semi-Structured Sparsity for Large Language Models |
26 Sep 2024 |
NVlabs/MaskLLM/eval_llama_ppl.py 7630a157a3b32ab9 |
unverified |
no licence file found · pointer only |
| EfficientQAT: Efficient Quantization-Aware Training for Large Language Models |
10 Jul 2024 |
opengvlab/efficientqat/datautils_block.py 2d9448699cce6e63 |
unverified |
MIT (permissive) |
| LeanQuant: Accurate Large Language Model Quantization with Loss-Error-Aware Grid |
14 Jul 2024 |
LeanModels/LeanQuant/datautils.py 86ac8f1de9c0550b |
unverified |
no licence file found · pointer only |
| Composable Interventions for Language Models |
9 Jul 2024 |
hartvigsen-group/composable-interventions/sparsellm/lib/data.py 823f33725cd8f75d |
unverified |
no licence file found · pointer only |
| Composable Interventions for Language Models |
9 Jul 2024 |
hartvigsen-group/composable-interventions/sparsellm/lib/datautils.py 1ebe223f71f863bc |
unverified |
no licence file found · pointer only |
| LLMBox: A Comprehensive Library for Large Language Models |
8 Jul 2024 |
RUCAIBox/LLMBox/training/gptq.py 3a8ad8ccd4b56839 |
unverified |
MIT (permissive) |
| Rethinking Pruning Large Language Models: Benefits and Pitfalls of Reconstruction Error Minimization |
21 Jun 2024 |
log-postech/rethinking-llm-pruning/lib/data.py 112fa6e5a362cc14 |
unverified |
no licence file found · pointer only |
| Evaluating the Generalization Ability of Quantized LLMs: Benchmark, Analysis, and Toolbox |
15 Jun 2024 |
tsingmaoai/mi-optimize/mi_optimize/datasets/data_loader.py 0f169d61e5b5e02a |
unverified |
licence not identified · pointer only |
| ShiftAddLLM: Accelerating Pretrained LLMs via Post-Training Multiplication-Less Reparameterization |
10 Jun 2024 |
gatech-eic/shiftaddllm/datautils.py 3b7f82daf1a2f6d5 |
unverified |
Apache-2.0 (permissive) |
| Pruner-Zero: Evolving Symbolic Pruning Metric from scratch for Large Language Models |
5 Jun 2024 |
pprp/pruner-zero/lib/data.py a271ec700d8df453 |
unverified |
MIT (permissive) |
| SOUL: Unlocking the Power of Second-Order Optimization for LLM Unlearning |
28 Apr 2024 |
optml-group/soul/src/dataset/dataset.py 7630a157a3b32ab9 |
unverified |
MIT (permissive) |
| FrameQuant: Flexible Low-Bit Quantization for Transformers |
10 Mar 2024 |
vsingh-group/framequant/datautils.py 4d29e98e5f0e4149 |
unverified |
no licence file found · pointer only |
| BESA: Pruning Large Language Models with Blockwise Parameter-Efficient Sparsity Allocation |
18 Feb 2024 |
linkanonymous/besa/utils/data.py 51a53fa33d2d9a6f |
unverified |
no licence file found · pointer only |
| Get More with LESS: Synthesizing Recurrence with KV Cache Compression for Efficient LLM Inference |
14 Feb 2024 |
hdong920/less/src/data_processing.py e17b6c1ff661e9bd |
unverified |
no licence file found · pointer only |
| Fast and Effective Weight Update for Pruned Large Language Models |
1 Jan 2024 |
fmfi-compbio/admm-pruning/lib/data.py 112fa6e5a362cc14 |
unverified |
MIT (permissive) |
| The LLM Surgeon |
28 Dec 2023 |
qualcomm-ai-research/llm-surgeon/datautils.py 4b6dab2040cdb423 |
unverified |
BSD-3-Clause-Clear · pointer only |
| Fluctuation-based Adaptive Structured Pruning for Large Language Models |
19 Dec 2023 |
casia-iva-lab/flap/lib/data.py 6ccf0fe3fd4574d5 |
unverified |
Apache-2.0 (permissive) |
| Beyond Size: How Gradients Shape Pruning Decisions in Large Language Models |
8 Nov 2023 |
rocktimjyotidas/gblm-pruner/gradient_computation.py 362bd8bd1eddbfc5 |
unverified |
MIT (permissive) |
| Beyond Size: How Gradients Shape Pruning Decisions in Large Language Models |
8 Nov 2023 |
rocktimjyotidas/gblm-pruner/lib/data.py 5cbbb830025b49e7 |
unverified |
MIT (permissive) |
| Atom: Low-bit Quantization for Efficient and Accurate LLM Serving |
29 Oct 2023 |
efeslab/atom/model/datautils.py eb9d2957b3161128 |
ran
|
no licence file found · pointer only |
| QUIK: Towards End-to-End 4-Bit Inference on Generative Large Language Models |
13 Oct 2023 |
ist-daslab/quik/experiments/datautils.py 980b7a8e42ae4a52 |
ran
|
Apache-2.0 (permissive) |
| Dynamic Sparse No Training: Training-Free Fine-tuning for Sparse LLMs |
13 Oct 2023 |
zyxxmu/dsnot/lib/prune.py 7630a157a3b32ab9 |
unverified |
no licence file found · pointer only |
| Compressing LLMs: The Truth is Rarely Pure and Never Simple |
2 Oct 2023 |
VITA-Group/llm-kick/GPTQ_experiment/lib/data.py c00c627524c6a86f |
unverified |
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/datautils.py 91dba77fa391e15e |
unverified |
Apache-2.0 (permissive) |
| Llama 2: Open Foundation and Fine-Tuned Chat Models |
18 Jul 2023 |
squeezeailab/squeezellm/squeezellm/datautils.py 92dc709e4e73e133 |
unverified |
MIT (permissive) |
| A Simple and Effective Pruning Approach for Large Language Models |
20 Jun 2023 |
crystaleye42/eval-safety/lib/prune.py 9660cb0c932e836e |
unverified |
MIT (permissive) |
| A Simple and Effective Pruning Approach for Large Language Models |
20 Jun 2023 |
qiaoxiao7282/seft/lib/prune_all.py 112fa6e5a362cc14 |
unverified |
no licence file found · pointer only |
| A Simple and Effective Pruning Approach for Large Language Models |
20 Jun 2023 |
locuslab/wanda/lib/prune.py 5a7a61a0235b3907 |
unverified |
MIT (permissive) |
| RPTQ: Reorder-based Post-training Quantization for Large Language Models |
3 Apr 2023 |
hahnyuan/rptq4llm/datautils.py a7b3cccc9ad0d188 |
unverified |
MIT (permissive) |
| arXiv:openreview_d3RFDLBw01 |
|
AI2C-Lab/STLA/data_utils.py 3e8381ec040b34cc |
unverified |
Apache-2.0 (permissive) |
| arXiv:openreview_4iupzej9nT |
|
hikvision-research/STEP/step/lib/data.py 49637fd9dbf67223 |
unverified |
Apache-2.0 (permissive) |
| arXiv:aaai_28960 |
|
CASIA-IVA-Lab/FLAP/lib/data.py 6ccf0fe3fd4574d5 |
unverified |
Apache-2.0 (permissive) |
| arXiv:2025.acl-long.498 |
|
OpenGVLab/EfficientQAT/datautils_block.py 2d9448699cce6e63 |
unverified |
MIT (permissive) |
| arXiv:2024.findings-naacl.145 |
|
LianjiaTech/BELLE/models/gptq/datautils.py 91dba77fa391e15e |
unverified |
Apache-2.0 (permissive) |
| arXiv:2024.findings-emnlp.579 |
|
RazvanDu/DynamicSlicing/src/slicegpt/data.lib.py 7630a157a3b32ab9 |
unverified |
MIT (permissive) |