zjc

chuanyizjc's activity

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

New activity in nvidia/Llama-3_1-Nemotron-Ultra-253B-v1 4 months ago

sglang supports Llama-3_1-Nemotron-Ultra-253B-v1 ?

#12 opened 4 months ago by

chuanyizjc

FP8 and FP4

2

#5 opened 4 months ago by

whatever1983

New activity in nvidia/Llama-3_1-Nemotron-Ultra-253B-v1-FP8 4 months ago

FP8 dont take?

#4 opened 4 months ago by

chuanyizjc

dont run FP8, error

1

#3 opened 4 months ago by

chuanyizjc

New activity in nvidia/Llama-3_1-Nemotron-Ultra-253B-v1 4 months ago

benchmark test use vllm ? input/output=500/2000 ？

2

#6 opened 4 months ago by

chuanyizjc