ScalingIntelligence / CATSLinks
β29Updated 10 months ago
Alternatives and similar repositories for CATS
Users that are interested in CATS are comparing it to the libraries listed below
Sorting:
- SQUEEZED ATTENTION: Accelerating Long Prompt LLM Inferenceβ54Updated 10 months ago
- HALO: Hadamard-Assisted Low-Precision Optimization and Training method for finetuning LLMs. π The official implementation of https://arxβ¦β23Updated 7 months ago
- β142Updated 7 months ago
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLMβ168Updated last year
- Activation-aware Singular Value Decomposition for Compressing Large Language Modelsβ80Updated 11 months ago
- β29Updated last year
- Pytorch implementation of our paper accepted by ICML 2024 -- CaM: Cache Merging for Memory-efficient LLMs Inferenceβ46Updated last year
- LLM Inference with Microscaling Formatβ31Updated 10 months ago
- β35Updated last year
- β46Updated 11 months ago
- β38Updated last year
- [EMNLP 2024] RoLoRA: Fine-tuning Rotated Outlier-free LLMs for Effective Weight-Activation Quantizationβ38Updated last year
- β20Updated last year
- Official Pytorch Implementation of "Outlier Weighed Layerwise Sparsity (OWL): A Missing Secret Sauce for Pruning LLMs to High Sparsity"β72Updated 3 months ago
- Boosting 4-bit inference kernels with 2:4 Sparsityβ82Updated last year
- β22Updated 11 months ago
- [ICLR 2025] TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attentionβ47Updated 2 months ago
- β129Updated 4 months ago
- The evaluation framework for training-free sparse attention in LLMsβ100Updated 3 months ago
- Official Implementation of SLEB: Streamlining LLMs through Redundancy Verification and Elimination of Transformer Blocksβ37Updated 8 months ago
- This repo contains the source code for: Model Tells You What to Discard: Adaptive KV Cache Compression for LLMsβ39Updated last year
- β82Updated 8 months ago
- GPU operators for sparse tensor operationsβ35Updated last year
- AFPQ code implementationβ23Updated last year
- Official Repo for SparseLLM: Global Pruning of LLMs (NeurIPS 2024)β66Updated 6 months ago
- β60Updated last year
- Sirius, an efficient correction mechanism, which significantly boosts Contextual Sparsity models on reasoning tasks while maintaining itsβ¦β22Updated last year
- Efficient Expert Pruning for Sparse Mixture-of-Experts Language Models: Enhancing Performance and Reducing Inference Costsβ19Updated 9 months ago
- [ICML24] Pruner-Zero: Evolving Symbolic Pruning Metric from scratch for LLMsβ94Updated 10 months ago
- [COLM 2025] Official PyTorch implementation of "Quantization Hurts Reasoning? An Empirical Study on Quantized Reasoning Models"β54Updated 2 months ago