amirzandieh / QJL
QJL: 1-Bit Quantized JL transform for KV Cache Quantization with Zero Overhead
☆22Updated 2 months ago
Alternatives and similar repositories for QJL:
Users that are interested in QJL are comparing it to the libraries listed below
- 16-fold memory access reduction with nearly no loss☆86Updated last week
- A GPU-optimized system for efficient long-context LLMs decoding with low-bit KV cache.☆23Updated last week
- [ICML 2024 Oral] Any-Precision LLM: Low-Cost Deployment of Multiple, Different-Sized LLMs☆100Updated 3 months ago
- ☆52Updated last year
- ☆38Updated 8 months ago
- QAQ: Quality Adaptive Quantization for LLM KV Cache☆47Updated last year
- Boosting 4-bit inference kernels with 2:4 Sparsity☆71Updated 6 months ago
- [ICLR 2025] Palu: Compressing KV-Cache with Low-Rank Projection☆94Updated last month
- [ICLR 2025] TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attention☆31Updated last month
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆158Updated 8 months ago
- ArkVale: Efficient Generative LLM Inference with Recallable Key-Value Eviction (NIPS'24)☆32Updated 3 months ago
- PyTorch library for cost-effective, fast and easy serving of MoE models.☆157Updated this week
- SliM-LLM: Salience-Driven Mixed-Precision Quantization for Large Language Models☆28Updated 7 months ago
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆111Updated 3 months ago
- [ICML 2024] KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache☆281Updated 2 months ago
- ☆67Updated 2 months ago
- ☆122Updated last month
- Fast Matrix Multiplications for Lookup Table-Quantized LLMs☆235Updated last month
- Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity☆202Updated last year
- ☆53Updated last year
- Official Pytorch Implementation of "Outlier Weighed Layerwise Sparsity (OWL): A Missing Secret Sauce for Pruning LLMs to High Sparsity"☆59Updated 9 months ago
- ShiftAddLLM: Accelerating Pretrained LLMs via Post-Training Multiplication-Less Reparameterization☆104Updated 5 months ago
- SQUEEZED ATTENTION: Accelerating Long Prompt LLM Inference☆45Updated 4 months ago
- PyTorch implementation of paper "Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipeline".☆85Updated last year
- An algorithm for weight-activation quantization (W4A4, W4A8) of LLMs, supporting both static and dynamic quantization☆124Updated 2 months ago
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆301Updated 9 months ago
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆265Updated 4 months ago
- ☆55Updated 9 months ago
- QQQ is an innovative and hardware-optimized W4A8 quantization solution for LLMs.☆109Updated 3 weeks ago
- AFPQ code implementation☆20Updated last year