kv-cache

A Golang implemented Redis Server and Cluster. Go 语言实现的 Redis 服务器和分布式集群

Unified KV Cache Compression Methods for Auto-Regressive Models

LLM notes, including model inference, transformer model structure, and llm framework code analysis notes.

Achieve the llama3 inference step-by-step, grasp the core concepts, master the process derivation, implement the code.

LLM KV cache compression made easy

[NeurIPS'23] H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models.

Awesome-LLM-KV-Cache: A curated list of 📙Awesome LLM KV Cache Papers with Codes.

Block Transformer: Global-to-Local Language Modeling for Fast Inference (NeurIPS 2024)

HierarchicalKV is a part of NVIDIA Merlin and provides hierarchical key-value storage to meet RecSys requirements. The key capability of HierarchicalKV is to store key-value feature-embeddings on high-bandwidth memory (HBM) of GPUs and in host memory. It also can be used as a generic key-value storage.

Completion After Prompt Probability. Make your LLM make a choice

This repository contains an implementation of the LLaMA 2 (Large Language Model Meta AI) model, a Generative Pretrained Transformer (GPT) variant. The implementation focuses on the model architecture and the inference process. The code is restructured and heavily commented to facilitate easy understanding of the key parts of the architecture.

Easy control for Key-Value Constrained Generative LLM Inference(https://arxiv.org/abs/2402.06262)

Notes about LLaMA 2 model

Mistral and Mixtral (MoE) from scratch

Fine-Tuned Mistral 7B Persian Large Language Model LLM / Persian Mistral 7B

Image Captioning With MobileNet-LLaMA 3

Simple and easy to understand PyTorch implementation of Large Language Model (LLM) GPT and LLAMA from scratch with detailed steps. Implemented: Byte-Pair Tokenizer, Rotational Positional Embedding (RoPe), SwishGLU, RMSNorm, Mixture of Experts (MOE). Tested on Taylor Swift song lyrics dataset.

SCAC strategy for efficient and effective KV cache eviction in LLMs

Java-based caching solution designed to temporarily store key-value pairs with a specified time-to-live (TTL) duration.