InfiniAI Lab

university

https://www.infini-ai-lab.cmu.edu/

InfiniAILab

Activity Feed Request to join this org

AI & ML interests

ML algorithms and systems

Recent Activity

ZMC2019 updated a model 7 days ago

InfiniAILab/QwQ-32B-FP8

ZMC2019 published a model 7 days ago

InfiniAILab/QwQ-32B-FP8

ZMC2019 updated a collection 9 days ago

Open-R1 Reproduce

View all activity

InfiniAILab's activity

ZMC2019

updated a model 7 days ago

InfiniAILab/QwQ-32B-FP8

Updated 7 days ago • 145

ZMC2019

published a model 7 days ago

InfiniAILab/QwQ-32B-FP8

Updated 7 days ago • 145

ZMC2019

updated a collection 9 days ago

Open-R1 Reproduce

Reproduce Deepseek distilled models based on open-r1. • 4 items • Updated 9 days ago

ZMC2019

in InfiniAILab/QwQ-0.5B 10 days ago

QwQ 1.5B version too?

#1 opened 11 days ago by

ZMC2019

updated a collection 11 days ago

Draft Models

Draft models for Llama, Qwen, QwQ, Mistral ... • 5 items • Updated 11 days ago

ZMC2019

updated a collection 14 days ago

Draft Models

Draft models for Llama, Qwen, QwQ, Mistral ... • 5 items • Updated 11 days ago

ZMC2019

updated a model 14 days ago

InfiniAILab/QwQ-0.5B

Updated 14 days ago • 687 • 3

ZMC2019

published a model 14 days ago

InfiniAILab/QwQ-0.5B

Updated 14 days ago • 687 • 3

ZMC2019

updated a collection 14 days ago

Open-R1 Reproduce

Reproduce Deepseek distilled models based on open-r1. • 4 items • Updated 9 days ago

ZMC2019

updated a model 14 days ago

InfiniAILab/OpenR1-Qwen-7B-Math-Instruct

Text Generation • Updated 14 days ago • 233

ZMC2019

updated 2 collections 14 days ago

Open-R1 Reproduce

Reproduce Deepseek distilled models based on open-r1. • 4 items • Updated 9 days ago

Draft Models

Draft models for Llama, Qwen, QwQ, Mistral ... • 5 items • Updated 11 days ago

ZMC2019

updated a model 14 days ago

InfiniAILab/Mistral-150M-Instruct

Text Generation • Updated 14 days ago • 14

ZMC2019

published a model 14 days ago

InfiniAILab/Mistral-150M-Instruct

Text Generation • Updated 14 days ago • 14

ZMC2019

updated a dataset 14 days ago

InfiniAILab/gsm8k

Viewer • Updated 14 days ago • 1.32k • 177

ZMC2019

published a dataset 15 days ago

InfiniAILab/gsm8k

Viewer • Updated 14 days ago • 1.32k • 177

beidic

authored a paper about 1 month ago

HeadInfer: Memory-Efficient LLM Inference by Head-wise Offloading

Paper • 2502.12574 • Published Feb 18 • 11