#Long-context
Showing 24 of 24 repositories tagged #long-context, ranked by stars
Official release of InternLM series (InternLM, InternLM2, InternLM2.5, InternLM3).
Code and documents of LongLoRA and LongAlpaca (ICLR 2024 Oral)
[ICLR 2025] LongWriter: Unleashing 10,000+ Word Generation from Long Context LLMs
LongBench v2 and LongBench (ACL 25'&24')
LLM KV cache compression made easy
Implementation of MEGABYTE, Predicting Million-byte Sequences with Multiscale Transformers, in Pytorch
LongCite: Enabling LLMs to Generate Fine-grained Citations in Long-context QA
KVarN is a native vLLM KV-cache quantization backend for your agents: 3-5x more context, throughput above FP16, and FP16-level accuracy. Calibration-free, one flag.
Implementation of Recurrent Memory Transformer, Neurips 2022 paper, in Pytorch
The code of our paper "InfLLM: Unveiling the Intrinsic Capacity of LLMs for Understanding Extremely Long Sequences with Training-Free Memory"
AI API 中转站检测工具：Claude 中转站检测、OpenAI 中转站检测、Gemini 中转站检测，中转站真伪检测、长上下文验证、思维签名验证、中转站红黑榜，自托管开源。
Awesome GPT-5.6 API prompts, use cases, and integrations — 60 curated real-world cases for OpenAI's latest frontier model.
[EMNLP 2024 (Oral)] Leave No Document Behind: Benchmarking Long-Context LLMs with Extended Multi-Doc QA
[EMNLP 2024] LongRAG: A Dual-perspective Retrieval-Augmented Generation Paradigm for Long-Context Question Answering
Implementation of Perceiver AR, Deepmind's new long-context attention network based on Perceiver architecture, in Pytorch
Counting-Stars (★)
Advancing the frontier of efficient AI
a survey of long-context LLMs from four perspectives, architecture, infrastructure, training, and evaluation
My own attempt at a long context genomics model, leveraging recent advances in long context attention modeling (Flash Attention + other hierarchical methods)
EvoEmbedding: Evolvable Representations for Long-Context Retrieval and Agentic Memory
ConDB: The KV-Cache Native Context Database
[NeurIPS 2025 D&B (Spotlight🌟)] TIME: A Multi-level Benchmark for Temporal Reasoning of LLMs in Real-World Scenario
Unlimited context for Ai — give any LLM a billion-token memory. Open-source, local-first context + memory engine for agents. 🧠⚡
[ICLR2025] ReAttention, a training-free approach to break the maximum context length in length extrapolation