MInference 1.0: 10x Faster Million Context Inference with a Single GPU
•
12
Yucheng
liyucheng
AI & ML interests
Robust LLMs Evaluation and Efficient LLMs Inference.
Articles
Organizations
spaces
1
datasets
34
liyucheng/annotation_xw
Viewer
•
Updated
•
6k
•
62
liyucheng/fw-story-shard7
Viewer
•
Updated
•
7.89M
•
104
liyucheng/l-fineweb
Viewer
•
Updated
•
205M
•
5
liyucheng/annotation
Viewer
•
Updated
•
3.08k
•
207
liyucheng/parsed_arxiv
Viewer
•
Updated
•
49k
•
67
liyucheng/mind-interests
Viewer
•
Updated
•
50k
•
31
liyucheng/intention
Viewer
•
Updated
•
19.1k
•
1
liyucheng/long_paper_chunks
Viewer
•
Updated
•
368
•
31
liyucheng/mini_zh_news
Viewer
•
Updated
•
500
•
30
liyucheng/pg19-3k-long
Viewer
•
Updated
•
3k
•
31