A unified inference and post-training framework for accelerated video generation.

Light Video Generation Inference Framework

FlashInfer: Kernel Library for LLM Serving

Trainable fast and memory-efficient sparse attention

LongBench v2 and LongBench (ACL 25'&24')

The HELMET Benchmark

QeRL enables RL for 32B LLMs on a single H100 GPU.

If NVINT8 exists, the performance is ...

Triton implementation of FlashAttention2 that adds Custom Masks.

The evaluation framework for training-free sparse attention in LLMs

PaddleFormers is an easy-to-use library of pre-trained large language model zoo based on PaddlePaddle.

Unified KV Cache Compression Methods for Auto-Regressive Models

🚀 Efficient implementations of state-of-the-art linear attention models

VeOmni: Scaling Any Modality Model Training with Model-Centric Distributed Recipe Zoo

[NeurIPS'24 Spotlight, ICLR'25, ICML'25] To speed up Long-context LLMs' inference, approximate and dynamic sparse calculate the attention, which reduces inference latency by up to 10x for pre-filli…

This repo contains the source code for RULER: What’s the Real Context Size of Your Long-Context Language Models?

The official implementation of the EMNLP 2023 paper LLM-FP4

A general 2-8 bits quantization toolbox with GPTQ/AWQ/HQQ/VPTQ, and export to onnx/onnx-runtime easily.

An optimized quantization and inference library for running LLMs locally on modern consumer-class GPUs

Fused Qwen3 MoE layer for faster training, compatible with HF Transformers, LoRA, 4-bit quant, Unsloth

An open-source efficient deep learning framework/compiler, written in python.

verl: Volcano Engine Reinforcement Learning for LLMs

Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels

A high-throughput and memory-efficient inference and serving engine for LLMs