Shang Yang

Shangy's activity

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

authored 9 papers about 1 month ago

AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration

Paper • 2306.00978 • Published Jun 1, 2023 • 9

QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving

Paper • 2405.04532 • Published May 7, 2024

FlatFormer: Flattened Window Attention for Efficient Point Cloud Transformer

Paper • 2301.08739 • Published Jan 20, 2023

LongVILA: Scaling Long-Context Visual Language Models for Long Videos

Paper • 2408.10188 • Published Aug 19, 2024 • 52

HART: Efficient Visual Generation with Hybrid Autoregressive Transformer

Paper • 2410.10812 • Published Oct 14, 2024 • 17

Deep Compression Autoencoder for Efficient High-Resolution Diffusion Models

Paper • 2410.10733 • Published Oct 14, 2024 • 3

DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads

Paper • 2410.10819 • Published Oct 14, 2024 • 7

NVILA: Efficient Frontier Visual Language Models

Paper • 2412.04468 • Published Dec 5, 2024 • 59

LServe: Efficient Long-sequence LLM Serving with Unified Sparse Attention

Paper • 2502.14866 • Published Feb 20 • 13

upvoted a paper about 1 month ago

LServe: Efficient Long-sequence LLM Serving with Unified Sparse Attention

Paper • 2502.14866 • Published Feb 20 • 13

updated a dataset about 1 month ago

mit-han-lab/QServe-benchmarks

Updated Feb 15 • 124

updated a model about 1 month ago

mit-han-lab/Llama-3-8B-Instruct-Gradient-1048k-w8a8-per-channel-kv8-per-tensor

Updated Feb 14 • 26

published a model about 1 month ago

mit-han-lab/Llama-3-8B-Instruct-Gradient-1048k-w8a8-per-channel-kv8-per-tensor

Updated Feb 14 • 26

updated a model 2 months ago

Shangy/trans

Updated Jan 24

published a model 2 months ago

Shangy/trans

Updated Jan 24

upvoted a paper 4 months ago

NVILA: Efficient Frontier Visual Language Models

Paper • 2412.04468 • Published Dec 5, 2024 • 59

updated a model 11 months ago

mit-han-lab/Llama-2-13B-QServe

Text Generation • Updated May 4, 2024 • 21 • 1

updated a Space about 1 year ago

No application file

VILA Demo

🌖