mickqian

MickJ's activity

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

New activity in nvidia/Kimi-K2.5-NVFP4 3 months ago

[Question] gate_proj and up_proj weight_scale_2 mismatch in layer 3 of Kimi-K2.5-NVFP4

👀 3

1

#1 opened 3 months ago by

MickJ

New activity in stepfun-ai/Step-3.5-Flash 3 months ago

Deployment of Step-3.5-Flash (fp16) via sglang failed.

➕ 1

8

#17 opened 3 months ago by

zqzq71

New activity in stepfun-ai/Step3-VL-10B 3 months ago

add sglang support

#18 opened 3 months ago by

MickJ

add sglang support

#18 opened 3 months ago by

MickJ

add sglang support

#18 opened 3 months ago by

MickJ