henryzhongsc / longctx_bench
Official implementation for Yuan & Liu & Zhong et al., KV Cache Compression, But What Must We Give in Return? A Comprehensive Benchmark of Long Context Capable Approaches. EMNLP Findings 2024
β46Updated 3 weeks ago
Related projects β
Alternatives and complementary repositories for longctx_bench
- π° Must-read papers on KV Cache Compression (constantly updating π€).β120Updated this week
- MagicPIG: LSH Sampling for Efficient LLM Generationβ43Updated last week
- Fast and Robust Early-Exiting Framework for Autoregressive Language Models with Synchronized Parallel Decoding (EMNLP 2023 Long)β52Updated last month
- β31Updated 2 months ago
- Code for Palu: Compressing KV-Cache with Low-Rank Projectionβ54Updated this week
- The official implementation of the paper "Demystifying the Compression of Mixture-of-Experts Through a Unified Framework".β48Updated 2 weeks ago
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLMβ146Updated 3 months ago
- Multi-Candidate Speculative Decodingβ28Updated 6 months ago
- Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)β74Updated 3 weeks ago
- Code associated with the paper **Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding**β135Updated 5 months ago
- Spec-Bench: A Comprehensive Benchmark and Unified Evaluation Platform for Speculative Decoding (ACL 2024 Findings)β184Updated 2 weeks ago
- β107Updated 3 months ago
- β46Updated last year
- PyTorch implementation of paper "Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipeline".β74Updated last year
- Awesome-LLM-KV-Cache: A curated list of πAwesome LLM KV Cache Papers with Codes.β93Updated this week
- [NeurIPS'23] Speculative Decoding with Big Little Decoderβ85Updated 9 months ago
- The official implementation of paper: SimLayerKV: A Simple Framework for Layer-Level KV Cache Reduction.β35Updated 3 weeks ago
- QAQ: Quality Adaptive Quantization for LLM KV Cacheβ42Updated 7 months ago
- Quantized Side Tuning: Fast and Memory-Efficient Tuning of Quantized Large Language Modelsβ35Updated this week
- KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cacheβ240Updated last month
- Explorations into some recent techniques surrounding speculative decodingβ209Updated last year
- Long Context Extension and Generalization in LLMsβ39Updated last month
- Implementation of Kangaroo: Lossless Self-Speculative Decoding via Double Early Exitingβ41Updated 4 months ago
- Pytorch implementation of our paper accepted by ICML 2024 -- CaM: Cache Merging for Memory-efficient LLMs Inferenceβ25Updated 4 months ago
- β183Updated 6 months ago
- Official Pytorch Implementation of "Outlier Weighed Layerwise Sparsity (OWL): A Missing Secret Sauce for Pruning LLMs to High Sparsity"β51Updated 4 months ago
- Boosting 4-bit inference kernels with 2:4 Sparsityβ51Updated 2 months ago
- Official repository for LightSeq: Sequence Level Parallelism for Distributed Training of Long Context Transformersβ196Updated 2 months ago
- TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attentionβ21Updated last month
- The Official Implementation of Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inferenceβ35Updated this week