Shengliang Xu

shengliangx's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

updated a collection 30 minutes ago

Inference Optimized Checkpoints (with Model Optimizer)

Collection

A collection of generative models quantized and optimized for inference with Model Optimizer. • 96 items • Updated 30 minutes ago • 187

published a model about 4 hours ago

nvidia/GLM-5.3-Flash-NVFP4

Image-Text-to-Text • 169B • Updated about 7 hours ago • 22

updated a model about 7 hours ago

nvidia/GLM-5.3-Flash-NVFP4

Image-Text-to-Text • 169B • Updated about 7 hours ago • 22

updated 2 models 5 days ago

nvidia/Qwen3.8-27B-NVFP4

Text Generation • 18B • Updated about 18 hours ago • 52

nvidia/Qwen3.8-2.4T-A95B-NVFP4

Text Generation • 1.3T • Updated 5 days ago • 1.37k • 14

New activity in nvidia/Qwen3.8-2.4T-A95B-NVFP4 8 days ago

Document NVFP4 KV cache usage and evaluation

👍 1

#1 opened 9 days ago by

meenchen

published a model 13 days ago

nvidia/Qwen3.8-2.4T-A95B-NVFP4

Text Generation • 1.3T • Updated 5 days ago • 1.37k • 14

New activity in nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16 5 months ago

generation using transformers hit device mismatch issue

#23 opened 5 months ago by

shengliangx

New activity in nvidia/Qwen2.5-VL-7B-Instruct-FP8 9 months ago

update config for exclude modules

#3 opened 9 months ago by

shengliangx

New activity in nvidia/Llama-4-Scout-17B-16E-Instruct-NVFP4 9 months ago

update config for exclude modules

#3 opened 9 months ago by

shengliangx

New activity in nvidia/Llama-4-Scout-17B-16E-Instruct-FP8 9 months ago

update config for exclude modules

#1 opened 9 months ago by

shengliangx

New activity in nvidia/Qwen2.5-VL-7B-Instruct-NVFP4 9 months ago

Use actual module path in ignore

2

#2 opened 9 months ago by

shengliangx

New activity in nvidia/Llama-4-Maverick-17B-128E-Eagle3 over 1 year ago

add model configs and weights, update README

#1 opened over 1 year ago by

shengliangx

add model configs and weights, update README

#1 opened over 1 year ago by

shengliangx