thu-ml / Adaptive-Sparse-TrainerLinks
Official implementation for "Pruning Large Language Models with Semi-Structural Adaptive Sparse Training" (AAAI 2025)
☆12Updated 6 months ago
Alternatives and similar repositories for Adaptive-Sparse-Trainer
Users that are interested in Adaptive-Sparse-Trainer are comparing it to the libraries listed below
Sorting:
- ☆10Updated 8 months ago
- ☆24Updated last month
- [ICLR2025]: OSTQuant: Refining Large Language Model Quantization with Orthogonal and Scaling Transformations for Better Distribution Fitt…☆61Updated 2 months ago
- [NeurIPS 2024 Oral🔥] DuQuant: Distributing Outliers via Dual Transformation Makes Stronger Quantized LLMs.☆161Updated 8 months ago
- An algorithm for weight-activation quantization (W4A4, W4A8) of LLMs, supporting both static and dynamic quantization☆137Updated last month
- QAQ: Quality Adaptive Quantization for LLM KV Cache☆51Updated last year
- Official code implementation for 2025 ICLR accepted paper "Dobi-SVD : Differentiable SVD for LLM Compression and Some New Perspectives"☆34Updated 3 months ago
- Code Repository for the NeurIPS 2024 Paper "Toward Efficient Inference for Mixture of Experts".☆16Updated 7 months ago
- A sparse attention kernel supporting mix sparse patterns☆238Updated 4 months ago
- Efficient 2:4 sparse training algorithms and implementations☆54Updated 6 months ago
- Code Repository of Evaluating Quantized Large Language Models☆124Updated 9 months ago
- The Official Implementation of Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inference☆79Updated 5 months ago
- ☆42Updated 7 months ago
- [ICLR 2025] Palu: Compressing KV-Cache with Low-Rank Projection☆123Updated 4 months ago
- LLM Inference with Microscaling Format☆23Updated 7 months ago
- 16-fold memory access reduction with nearly no loss☆99Updated 3 months ago
- Official Pytorch Implementation of "Outlier Weighed Layerwise Sparsity (OWL): A Missing Secret Sauce for Pruning LLMs to High Sparsity"☆69Updated last year
- ☆51Updated 11 months ago
- Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference☆113Updated last month
- Github Repo for OATS: Outlier-Aware Pruning through Sparse and Low Rank Decomposition☆13Updated 2 months ago
- [NeurIPS 2024] The official implementation of ZipCache: Accurate and Efficient KV Cache Quantization with Salient Token Identification☆22Updated 2 months ago
- [ICML 2025] Official PyTorch implementation of "FlatQuant: Flatness Matters for LLM Quantization"☆138Updated last month
- The code repository of "MBQ: Modality-Balanced Quantization for Large Vision-Language Models"☆40Updated 3 months ago
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆297Updated 7 months ago
- Official Implementation of SLEB: Streamlining LLMs through Redundancy Verification and Elimination of Transformer Blocks☆37Updated 4 months ago
- Code implementation of GPTAQ (https://arxiv.org/abs/2504.02692)☆47Updated 3 weeks ago
- Activation-aware Singular Value Decomposition for Compressing Large Language Models☆72Updated 8 months ago
- ☆26Updated 7 months ago
- Official PyTorch implementation of "Quantization Hurts Reasoning? An Empirical Study on Quantized Reasoning Models"☆36Updated 3 weeks ago
- [ICML 2025] SliM-LLM: Salience-Driven Mixed-Precision Quantization for Large Language Models☆33Updated 10 months ago