AI & ML interests

MoE architectures, Chimera models, Assembly of Experts

Recent Activity

BM-TNG  updated a model about 2 months ago
tngtech/DeepSeek-R1T-Chimera
BM-TNG  updated a model about 2 months ago
tngtech/DeepSeek-TNG-R1T2-Chimera
View all activity

Articles

BM-TNG 
published an article 9 months ago
view article
Article

How Long Prompts Block Other Requests - Optimizing LLM Performance

•
10
SR-TNG 
published an article 11 months ago
view article
Article

Finetuning olmOCR to be a faithful OCR-Engine

•
19
BM-TNG 
published an article 11 months ago
view article
Article

Prefill and Decode for Concurrent Requests - Optimizing LLM Performance

•
67
BM-TNG 
published an article 12 months ago
view article
Article

Efficient Request Queueing – Optimizing LLM Performance

•
24