whyNLP / LCKV
Layer-Condensed KV cache w/ 10 times larger batch size, fewer params and less computation. Dramatic speed up with better task performance. Accepted to ACL 2024.
☆137Updated this week
Related projects ⓘ
Alternatives and complementary repositories for LCKV
- ☆121Updated 9 months ago
- Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clusters☆104Updated last month
- Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆70Updated this week
- Block Transformer: Global-to-Local Language Modeling for Fast Inference (Official Code)☆133Updated last month
- Experiments on speculative sampling with Llama models☆117Updated last year
- Cold Compress is a hackable, lightweight, and open-source toolkit for creating and benchmarking cache compression methods built on top of…☆86Updated 3 months ago
- ☆95Updated last month
- Unofficial implementation for the paper "Mixture-of-Depths: Dynamically allocating compute in transformer-based language models"☆134Updated 4 months ago
- This is the official repository for Inheritune.☆105Updated last month
- The official repo for "LLoCo: Learning Long Contexts Offline"☆110Updated 4 months ago
- Code for exploring Based models from "Simple linear attention language models balance the recall-throughput tradeoff"☆212Updated 2 months ago
- Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)☆74Updated 3 weeks ago
- Official implementation for 'Extending LLMs’ Context Window with 100 Samples'☆73Updated 9 months ago
- ☆183Updated 6 months ago
- The source code of our work "Prepacking: A Simple Method for Fast Prefilling and Increased Throughput in Large Language Models"☆56Updated 3 weeks ago
- Cascade Speculative Drafting☆26Updated 7 months ago
- Positional Skip-wise Training for Efficient Context Window Extension of LLMs to Extremely Length (ICLR 2024)☆200Updated 5 months ago
- Simple implementation of Speculative Sampling in NumPy for GPT-2.☆89Updated last year
- Simple and efficient pytorch-native transformer training and inference (batched)☆61Updated 7 months ago
- Code repository for the c-BTM paper☆105Updated last year
- BABILong is a benchmark for LLM evaluation using the needle-in-a-haystack approach.☆150Updated 2 months ago
- Multipack distributed sampler for fast padding-free training of LLMs☆175Updated 3 months ago
- ☆49Updated 6 months ago
- Easy control for Key-Value Constrained Generative LLM Inference(https://arxiv.org/abs/2402.06262)☆56Updated 8 months ago
- Parameter-Efficient Sparsity Crafting From Dense to Mixture-of-Experts for Instruction Tuning on General Tasks☆129Updated last month
- The code for the paper: "Same Task, More Tokens: the Impact of Input Length on the Reasoning Performance of Large Language Models"☆49Updated 4 months ago
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆146Updated 3 months ago
- A toolkit for fine-tuning, inferencing, and evaluating GreenBitAI's LLMs.☆72Updated 3 weeks ago
- open-source code for paper: Retrieval Head Mechanistically Explains Long-Context Factuality☆156Updated 3 months ago
- Official PyTorch implementation of DistiLLM: Towards Streamlined Distillation for Large Language Models (ICML 2024)☆133Updated last month