Tom

MarjorTom's activity

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

New activity in deepseek-ai/DeepSeek-V4-Pro 13 days ago

关于 "Observations and Proposals" 中激活函数建议的疑问：去掉 gate projection 为何能放宽 EP 带宽要求？

2

#126 opened 14 days ago by

MarjorTom

New activity in deepseek-ai/DeepSeek-V4-Pro 14 days ago

关于 "Observations and Proposals" 中激活函数建议的疑问：去掉 gate projection 为何能放宽 EP 带宽要求？

2

#126 opened 14 days ago by

MarjorTom