Haocheng Xi

Xihc20's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes

upvoted a paper 10 days ago

SageAttention2 Technical Report: Accurate 4 Bit Attention for Plug-and-play Inference Acceleration

Paper • 2411.10958 • Published Nov 17, 2024 • 52

upvoted a paper 30 days ago

NVILA: Efficient Frontier Visual Language Models

Paper • 2412.04468 • Published about 1 month ago • 57

upvoted an article about 2 months ago

view article

Article

Unbelievable! Run 70B LLM Inference on a Single 4GB GPU with This NEW Technique

By •

Nov 30, 2023

• 30

upvoted a paper about 2 months ago

T2V-CompBench: A Comprehensive Benchmark for Compositional Text-to-video Generation

Paper • 2407.14505 • Published Jul 19, 2024 • 26

upvoted 2 papers 2 months ago

COAT: Compressing Optimizer states and Activation for Memory-Efficient FP8 Training

Paper • 2410.19313 • Published Oct 25, 2024 • 19

PUMA: Empowering Unified MLLM with Multi-granular Visual Generation

Paper • 2410.13861 • Published Oct 17, 2024 • 53

upvoted a paper 3 months ago

SageAttention: Accurate 8-Bit Attention for Plug-and-play Inference Acceleration

Paper • 2410.02367 • Published Oct 3, 2024 • 47

upvoted a paper over 1 year ago

Training Transformers with 4-bit Integers

Paper • 2306.11987 • Published Jun 21, 2023 • 22