MInference 1.0: 10x Faster Million Context Inference with a Single GPU
•
11
Yucheng
liyucheng
AI & ML interests
Robust LLMs Evaluation and Efficient LLMs Inference.
Articles
Organizations
Papers
2
spaces
1
datasets
29
liyucheng/fw-story-annotations
Updated
liyucheng/fw-story-annotations-v2
Updated
liyucheng/long_paper_chunks
Viewer
•
Updated
•
368
•
38
liyucheng/mini_zh_news
Viewer
•
Updated
•
500
•
36
liyucheng/pg19-3k-long
Viewer
•
Updated
•
3k
•
44
liyucheng/pg19-4k
Viewer
•
Updated
•
4k
•
105
liyucheng/pg19
Viewer
•
Updated
•
13.6k
•
97
liyucheng/reject_sampling
Viewer
•
Updated
•
10
•
15
liyucheng/ShareGPT90K
Viewer
•
Updated
•
90.7k
•
151
•
2
liyucheng/mmlu_test
Viewer
•
Updated
•
14k
•
44