NVlabs / MaskLLM
[NeurIPS 24 Spotlight] MaskLLM: Learnable Semi-structured Sparsity for Large Language Models
☆157Updated 2 months ago
Alternatives and similar repositories for MaskLLM:
Users that are interested in MaskLLM are comparing it to the libraries listed below
- [ACL 2024] Not All Experts are Equal: Efficient Expert Pruning and Skipping for Mixture-of-Experts Large Language Models☆85Updated 10 months ago
- Unofficial implementation for the paper "Mixture-of-Depths: Dynamically allocating compute in transformer-based language models"☆154Updated 9 months ago
- The official implementation of the paper <MoA: Mixture of Sparse Attention for Automatic Large Language Model Compression>☆121Updated 3 months ago
- [ICLR 2024 Spotlight] Code for the paper "Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy"☆74Updated 9 months ago
- Official Implementation of SLEB: Streamlining LLMs through Redundancy Verification and Elimination of Transformer Blocks☆35Updated last month
- An algorithm for weight-activation quantization (W4A4, W4A8) of LLMs, supporting both static and dynamic quantization☆121Updated last month
- Activation-aware Singular Value Decomposition for Compressing Large Language Models☆59Updated 5 months ago
- Awesome LLM pruning papers all-in-one repository with integrating all useful resources and insights.☆76Updated 3 months ago
- [ICML 2024] KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache☆279Updated 2 months ago
- Pruner-Zero: Evolving Symbolic Pruning Metric from scratch for LLMs☆80Updated 3 months ago
- Awesome list for LLM pruning.☆212Updated 3 months ago
- A family of compressed models obtained via pruning and knowledge distillation☆329Updated 4 months ago
- ☆43Updated 4 months ago
- [ICLR 2025] COAT: Compressing Optimizer States and Activation for Memory-Efficient FP8 Training☆164Updated last month
- ☆116Updated last month
- Official implementation of "DoRA: Weight-Decomposed Low-Rank Adaptation"☆123Updated 10 months ago
- [ICLR2025] Codebase for "ReMoE: Fully Differentiable Mixture-of-Experts with ReLU Routing", built on Megatron-LM.☆65Updated 3 months ago
- ☆194Updated 3 months ago
- The official implementation of the paper "What Matters in Transformers? Not All Attention is Needed".☆164Updated 3 months ago
- Code accompanying the paper "Massive Activations in Large Language Models"☆150Updated last year
- Implementation of the paper: "Mixture-of-Depths: Dynamically allocating compute in transformer-based language models"☆85Updated last week
- PB-LLM: Partially Binarized Large Language Models☆152Updated last year
- [ICLR 2025] DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads☆438Updated last month
- SliM-LLM: Salience-Driven Mixed-Precision Quantization for Large Language Models☆28Updated 7 months ago
- Official Pytorch Implementation of "Outlier Weighed Layerwise Sparsity (OWL): A Missing Secret Sauce for Pruning LLMs to High Sparsity"☆59Updated 8 months ago
- ☆220Updated 9 months ago
- [NeurIPS 2024 Oral🔥] DuQuant: Distributing Outliers via Dual Transformation Makes Stronger Quantized LLMs.☆147Updated 5 months ago
- The official implementation of the paper "Towards Efficient Mixture of Experts: A Holistic Study of Compression Techniques (TMLR)".☆61Updated this week