long-context

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

LLM KV cache compression made easy

Large Context Attention

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

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。

PyTorch implementation of Infini-Transformer from "Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention" (https://arxiv.org/abs/2404.07143)

Official implementation of 'Transformer-VQ: Linear-Time Transformers via Vector Quantization' (ICLR 2024)

WritingBench: A Comprehensive Benchmark for Generative Writing

[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 Infini-Transformer in Pytorch

My own attempt at a long context genomics model, leveraging recent advances in long context attention modeling (Flash Attention + other hierarchical methods)

Training-free KV cache compression via E8 lattice VQ. 2-bit KV that preserves retrieval (30/30 NIAH vs TurboQuant 0/30). Calibration-free, 9 architectures validated.

GLM-5.2 on 4x DGX Spark with adaptive MTP K2/K4/K5, FULL CUDA graphs, DCP2, 520K context, and a downloadable ARM64 runtime image.