amirzandieh / QJL
QJL: 1-Bit Quantized JL transform for KV Cache Quantization with Zero Overhead
☆22Updated this week
Alternatives and similar repositories for QJL:
Users that are interested in QJL are comparing it to the libraries listed below
- ☆51Updated 10 months ago
- QAQ: Quality Adaptive Quantization for LLM KV Cache☆45Updated 10 months ago
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆152Updated 6 months ago
- 16-fold memory access reduction with nearly no loss☆72Updated 2 months ago
- [ICLR 2025] TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attention☆26Updated last month
- Code for Palu: Compressing KV-Cache with Low-Rank Projection☆64Updated this week
- SliM-LLM: Salience-Driven Mixed-Precision Quantization for Large Language Models☆26Updated 5 months ago
- A sparse attention kernel supporting mix sparse patterns☆98Updated 3 months ago
- [ICML 2024] KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache☆269Updated last week
- Boosting 4-bit inference kernels with 2:4 Sparsity☆64Updated 4 months ago
- Sirius, an efficient correction mechanism, which significantly boosts Contextual Sparsity models on reasoning tasks while maintaining its…☆21Updated 4 months ago
- PyTorch library for cost-effective, fast and easy serving of MoE models.☆116Updated this week
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆105Updated last month
- Official PyTorch implementation of FlatQuant: Flatness Matters for LLM Quantization☆95Updated last week
- Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity☆195Updated last year
- QQQ is an innovative and hardware-optimized W4A8 quantization solution for LLMs.☆95Updated last month
- ShiftAddLLM: Accelerating Pretrained LLMs via Post-Training Multiplication-Less Reparameterization☆101Updated 3 months ago
- An algorithm for static activation quantization of LLMs☆112Updated 2 weeks ago
- Activation-aware Singular Value Decomposition for Compressing Large Language Models☆55Updated 3 months ago
- PyTorch bindings for CUTLASS grouped GEMM.☆61Updated 3 months ago
- Official implementation for Yuan & Liu & Zhong et al., KV Cache Compression, But What Must We Give in Return? A Comprehensive Benchmark o…☆61Updated last month
- Fast Hadamard transform in CUDA, with a PyTorch interface☆135Updated 8 months ago
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆236Updated 2 months ago
- Official Pytorch Implementation of "Outlier Weighed Layerwise Sparsity (OWL): A Missing Secret Sauce for Pruning LLMs to High Sparsity"☆57Updated 7 months ago
- [ICML 2024 Oral] Any-Precision LLM: Low-Cost Deployment of Multiple, Different-Sized LLMs☆93Updated last month
- Quantized Attention on GPU☆34Updated 2 months ago
- ☆31Updated 6 months ago
- [NeurIPS 2024] The official implementation of "Kangaroo: Lossless Self-Speculative Decoding for Accelerating LLMs via Double Early Exitin…☆48Updated 7 months ago
- ☆218Updated 9 months ago
- SeerAttention: Learning Intrinsic Sparse Attention in Your LLMs☆23Updated 2 months ago