Z Lab

university

https://z-lab.ai

z-lab

AI & ML interests

Efficient AI

Recent Activity

zhijianliu authored a paper 10 days ago

VLASH: Real-Time VLAs via Future-State-Aware Asynchronous Inference

liang2kl authored a paper 25 days ago

ParoQuant: Pairwise Rotation Quantization for Efficient Reasoning LLM Inference

zhijianliu authored a paper 25 days ago

ParoQuant: Pairwise Rotation Quantization for Efficient Reasoning LLM Inference

View all activity

Papers

ParoQuant: Pairwise Rotation Quantization for Efficient Reasoning LLM Inference

View all Papers

z-lab 's models 18

z-lab/Qwen3-4B-Thinking-2507-PARO

1B • Updated Oct 31 • 4

z-lab/DeepSeek-R1-Distill-Llama-8B-PARO

1B • Updated Oct 29 • 5

z-lab/Meta-Llama-3-70B-PARO

20B • Updated Oct 29 • 4

z-lab/Qwen3-14B-PARO

2B • Updated Oct 29 • 4

z-lab/Qwen3-14B-Base-PARO

2B • Updated Oct 29 • 7

z-lab/Qwen3-8B-PARO

1B • Updated Oct 29 • 7

z-lab/Qwen3-8B-Base-PARO

1B • Updated Oct 29 • 4

z-lab/Qwen3-4B-PARO

1B • Updated Oct 29 • 4

z-lab/Qwen3-4B-Base-PARO

1B • Updated Oct 29 • 3

z-lab/Qwen3-1.7B-PARO

0.7B • Updated Oct 29 • 3

z-lab/Qwen3-1.7B-Base-PARO

0.7B • Updated Oct 29 • 4

z-lab/Qwen3-0.6B-PARO

0.3B • Updated Oct 29 • 4

z-lab/Qwen3-0.6B-Base-PARO

0.3B • Updated Oct 29 • 4

z-lab/Llama-2-7b-hf-PARO

2B • Updated Oct 29 • 4

z-lab/Llama-3.1-8B-Instruct-PARO

3B • Updated Oct 29 • 3

z-lab/Meta-Llama-3-8B-PARO

1B • Updated Oct 29 • 210

z-lab/paroquant-checkpoints

z-lab/sparselora-svd-estimator

Other • Updated Jul 5 • 12 • 1