How Long Prompts Block Other Requests - Optimizing LLM Performance
• 14
AI & ML interests
MoE architectures, Chimera models, Assembly of Experts
Recent Activity
View all activity
Articles
Organization Card
TNG Technology Consulting GmbH
We solve hard IT problems.
Latest Research
Check out our latest research:
- DeepSeek-TNG-R1T2-Chimera
- DeepSeek-R1T-Chimera
- Mixture of Tunable Experts
Blog
Read our latest blog posts:
- Prefill and Decode for Concurrent Requests - Optimizing LLM Performance
- Finetuning olmOCR to be a faithful OCR-Engine
- Efficient Request Queueing – Optimizing LLM Performance
Follow us
models 7
tngtech/Qwen3.6-27B-NVFP4-GGUF
Text Generation • 27B • Updated • 2.72k • 2
tngtech/Kokoro-82M-int8-ov
Text-to-Speech • Updated • 329 • 1
tngtech/DeepSeek-R1T-Chimera
Text Generation • 685B • Updated • 136 • 273
tngtech/DeepSeek-TNG-R1T2-Chimera
Text Generation • 685B • Updated • 167 • 285
tngtech/Phi-3-mini-4k-instruct-sym-int4-channelwise-ov
Updated • 2
tngtech/olmOCR-7B-faithful
Image-Text-to-Text • 8B • Updated • 14 • 18
tngtech/OLMo-2-Instruct-Math-32B
Text Generation • 32B • Updated • 18 • 5
datasets 0
None public yet