zcli-charlie / Awesome-KV-Cache
☆22Updated last month
Related projects: ⓘ
- ☆29Updated 4 months ago
- ☆37Updated 5 months ago
- 16-fold memory access reduction with nearly no loss☆35Updated last month
- PyTorch implementation of paper "Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipeline".☆70Updated last year
- Multi-Candidate Speculative Decoding☆27Updated 4 months ago
- Code associated with the paper **Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding**☆127Updated 3 months ago
- An innovative method expediting LLMs via streamlined semi-autoregressive generation and draft verification.☆21Updated 7 months ago
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆134Updated 2 months ago
- Ouroboros: Speculative Decoding with Large Model Enhanced Drafting☆60Updated 6 months ago
- ☆29Updated 3 weeks ago
- QAQ: Quality Adaptive Quantization for LLM KV Cache☆42Updated 5 months ago
- Code for ACL2022 publication Transkimmer: Transformer Learns to Layer-wise Skim☆21Updated 2 years ago
- Official repository for LightSeq: Sequence Level Parallelism for Distributed Training of Long Context Transformers☆183Updated last month
- ☆65Updated 2 years ago
- A tiny yet powerful LLM inference system tailored for researching purpose. vLLM-equivalent performance with only 2k lines of code (2% of …☆84Updated 2 months ago
- ☆164Updated 4 months ago
- Boosting 4-bit inference kernels with 2:4 Sparsity☆47Updated 2 weeks ago
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆161Updated 2 months ago
- Spec-Bench: A Comprehensive Benchmark and Unified Evaluation Platform for Speculative Decoding (ACL 2024 Findings)☆156Updated 3 months ago
- Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity☆166Updated 11 months ago
- ☆60Updated last month
- ☆38Updated 4 months ago
- [NeurIPS'23] Speculative Decoding with Big Little Decoder☆84Updated 7 months ago
- Implementation of Kangaroo: Lossless Self-Speculative Decoding via Double Early Exiting☆39Updated 2 months ago
- ATC23 AE☆42Updated last year
- PyTorch library for cost-effective, fast and easy serving of MoE models.☆90Updated last month
- PyTorch bindings for CUTLASS grouped GEMM.☆57Updated 2 months ago
- Quantized Side Tuning: Fast and Memory-Efficient Tuning of Quantized Large Language Models☆27Updated last week
- PyTorch bindings for CUTLASS grouped GEMM.☆41Updated 3 weeks ago
- Repository of LV-Eval Benchmark☆41Updated 2 weeks ago