Paper (14)

SSM Vision Encoders for Visual Language Models

MSA: Memory Sparse Attention for Efficient End-to-End Memory Model Scaling to 100M Tokens

DreamID-Omni: Unified Controllable Audio-Video Generation Framework

Mixture of Depths Attention

IndexCache-Accelerating Sparse Attention via Cross-Layer Index Reuse

一种面向LLM推理的极简方法-从拒绝采样到Reinforce

Qwen3 技术报告

A Survey on Inference Engines for Large Language Models

A Survey on Efficient Inference for Large Language Models

Memo:Fine-grained Tensor Management For Ultra-long Context LLM Training

Fire-Flyer File System:3FS

A Survey on Multimodal Large Language Models

FAST 2025 数据一览

Burstable Cloud Block Storage with Data Processing Units

Cuda (2)

GDS cuFile

CUDA Graph

Pytorch (2)

PyTorch Mega-Cache 实现深度解读

PyTorch DDP梯度同步机制详解