Z Lab

university

Verified

https://z-lab.ai

AI & ML interests

Efficient AI

Recent Activity

jianchen0311 new activity about 1 hour ago

z-lab/Qwen3.5-9B-DFlash:Is it mandatory to use flash-attn?

jianchen0311 new activity about 7 hours ago

z-lab/Qwen3.6-27B-DFlash:Why is there a 4k ctx limit?

jianchen0311 new activity about 7 hours ago

z-lab/Qwen3.6-27B-DFlash:with latest sglang, gibberish output

View all activity

Papers

DFlash: Block Diffusion for Flash Speculative Decoding

ParoQuant: Pairwise Rotation Quantization for Efficient Reasoning LLM Inference

View all Papers

Collections 3

View 3 collections

models 35

z-lab/Qwen3.6-27B-DFlash

Text Generation • 2B • Updated 1 day ago • 7.61k • 141

z-lab/Qwen3.5-122B-A10B-DFlash

Text Generation • 0.5B • Updated 1 day ago • 853 • 5

z-lab/Qwen3.6-35B-A3B-DFlash

Text Generation • 0.5B • Updated 2 days ago • 30k • 173

z-lab/Kimi-K2.5-DFlash

Text Generation • 3B • Updated 10 days ago • 13.4k • 28

z-lab/gpt-oss-20b-DFlash

Text Generation • 0.8B • Updated 21 days ago • 1.67k • 19

z-lab/LLaMA3.1-8B-Instruct-DFlash-UltraChat

Text Generation • 1B • Updated 21 days ago • 3.49k • 2

z-lab/Qwen3-Coder-30B-A3B-DFlash

Text Generation • 0.5B • Updated 21 days ago • 1.54k • 28

z-lab/Qwen3-Coder-Next-DFlash

Text Generation • 0.5B • Updated 21 days ago • 2.15k • 9

z-lab/Qwen3.5-9B-DFlash

Text Generation • 1B • Updated 21 days ago • 8.87k • 27

z-lab/Qwen3.5-4B-DFlash

Text Generation • 0.5B • Updated 21 days ago • 16.4k • 15

datasets 7

z-lab/kimi-k26-regen

Viewer • Updated 6 days ago • 1M • 11 • 2

z-lab/humaneval-long

Viewer • Updated 13 days ago • 1k • 36

z-lab/gsm8k-filtered

Viewer • Updated Mar 25 • 1.31k • 9

z-lab/mt-bench-filtered

Viewer • Updated Mar 25 • 79 • 11

z-lab/mbpp-sanitized-filtered

Viewer • Updated Mar 25 • 256 • 21

z-lab/humaneval-filtered

Viewer • Updated Mar 25 • 137 • 10

z-lab/qwen3-4b-instruct-100k

Viewer • Updated Mar 25 • 100k • 22