mit-han-lab/SMEPO
Viewer • Updated • 2.05k • 9
HanLab-Dev
community
AI & ML interests
None defined yet.
Recent Activity
liurt1218
updated a
dataset 1 day ago
liurt1218
published a
dataset 1 day ago
Qinghao
authored a
paper 10 months ago
Shangy
authored 9
papers about 1 year ago
AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration
Paper • 2306.00978 • Published • 12
QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving
Paper • 2405.04532 • Published
FlatFormer: Flattened Window Attention for Efficient Point Cloud Transformer
Paper • 2301.08739 • Published
LongVILA: Scaling Long-Context Visual Language Models for Long Videos
Paper • 2408.10188 • Published • 52
HART: Efficient Visual Generation with Hybrid Autoregressive Transformer
Paper • 2410.10812 • Published • 18
Deep Compression Autoencoder for Efficient High-Resolution Diffusion Models
Paper • 2410.10733 • Published • 9
DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads
Paper • 2410.10819 • Published • 7
NVILA: Efficient Frontier Visual Language Models
Paper • 2412.04468 • Published • 60
LServe: Efficient Long-sequence LLM Serving with Unified Sparse Attention
Paper • 2502.14866 • Published • 13
Qinghao
authored 3
papers over 1 year ago
InternEvo: Efficient Long-sequence Large Language Model Training via Hybrid Parallelism and Redundant Sharding
Paper • 2401.09149 • Published • 1
LoongTrain: Efficient Training of Long-Sequence LLMs with Head-Context Parallelism
Paper • 2406.18485 • Published • 3
LongVILA: Scaling Long-Context Visual Language Models for Long Videos
Paper • 2408.10188 • Published • 52
Qinghao
authored a
paper over 2 years ago