cat538 / SKVQ
SKVQ: Sliding-window Key and Value Cache Quantization for Large Language Models
☆12Updated last month
Related projects ⓘ
Alternatives and complementary repositories for SKVQ
- ☆42Updated 7 months ago
- Official PyTorch implementation of FlatQuant: Flatness Matters for LLM Quantization☆59Updated this week
- A sparse attention kernel supporting mix sparse patterns☆53Updated 3 weeks ago
- QAQ: Quality Adaptive Quantization for LLM KV Cache☆42Updated 7 months ago
- Quantized Attention on GPU☆29Updated last week
- ☆34Updated 2 months ago
- QQQ is an innovative and hardware-optimized W4A8 quantization solution for LLMs.☆76Updated last month
- [ACL 2024] A novel QAT with Self-Distillation framework to enhance ultra low-bit LLMs.☆81Updated 5 months ago
- Puzzles for learning Triton, play it with minimal environment configuration!☆61Updated this week
- 16-fold memory access reduction with nearly no loss☆57Updated this week
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆196Updated last week
- High performance Transformer implementation in C++.☆80Updated last month
- ☆43Updated last month
- ☆70Updated 2 years ago
- PyTorch bindings for CUTLASS grouped GEMM.☆53Updated last week
- Summary of some awesome work for optimizing LLM inference☆35Updated this week
- ☆42Updated 4 months ago
- A tiny yet powerful LLM inference system tailored for researching purpose. vLLM-equivalent performance with only 2k lines of code (2% of …☆98Updated 4 months ago
- ☆79Updated 2 months ago
- MagicPIG: LSH Sampling for Efficient LLM Generation☆45Updated 2 weeks ago
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆146Updated 4 months ago
- ☆18Updated 3 months ago
- Official Repo for "LLM-PQ: Serving LLM on Heterogeneous Clusters with Phase-Aware Partition and Adaptive Quantization"☆26Updated 8 months ago
- ☆9Updated 5 months ago
- A parallelism VAE avoids OOM for high resolution image generation☆40Updated last month
- ☆12Updated 7 months ago
- PyTorch library for cost-effective, fast and easy serving of MoE models.☆101Updated 2 months ago
- Official implementation of the ICLR 2024 paper AffineQuant☆21Updated 7 months ago
- Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity☆178Updated last year
- ☆63Updated 3 months ago