ruikang liu

ruikangliu

·

ruikangliu

AI & ML interests

None yet

Recent Activity

upvoted a paper 3 days ago

G^2PTQ: Improving LLM Post-Training Quantization with Generalized Gradient Compensation

submitted a paper 3 days ago

G^2PTQ: Improving LLM Post-Training Quantization with Generalized Gradient Compensation

upvoted an article 2 months ago

Profiling in PyTorch (Part 3): Attention is all you profile

View all activity

Organizations

None yet

Collections 2

Papers 3

arxiv:2504.04823

arxiv:2410.09426

arxiv:2403.01241

models 9

ruikangliu/FlatQuant

Feature Extraction • Updated Sep 16, 2025 • 4

ruikangliu/DeepSeek-R1-Distill-Qwen-32B-quantized.gptq-gptqmodel-w4g128

33B • Updated Jun 10, 2025 • 18

ruikangliu/DeepSeek-R1-Distill-Qwen-14B-quantized.gptq-gptqmodel-w4g128

15B • Updated Jun 10, 2025 • 14

ruikangliu/DeepSeek-R1-Distill-Qwen-7B-quantized.gptq-gptqmodel-w4g128

8B • Updated Jun 10, 2025 • 17

ruikangliu/DeepSeek-R1-Distill-Qwen-1.5B-quantized.gptq-gptqmodel-w4g128

2B • Updated Jun 10, 2025 • 40

ruikangliu/DeepSeek-R1-Distill-Qwen-32B-quantized.awq-autoawq-w4g128

33B • Updated Jun 10, 2025 • 15

ruikangliu/DeepSeek-R1-Distill-Qwen-14B-quantized.awq-autoawq-w4g128

15B • Updated Jun 10, 2025 • 15

ruikangliu/DeepSeek-R1-Distill-Qwen-7B-quantized.awq-autoawq-w4g128

8B • Updated Jun 10, 2025 • 18

ruikangliu/DeepSeek-R1-Distill-Qwen-1.5B-quantized.awq-autoawq-w4g128

2B • Updated Jun 10, 2025 • 88

datasets 0

None public yet