fabian-roll
		
		
				
				·
				 
		
		
		
			AI & ML interests
		
		Large Language Models.
PhD in Topological Data Analysis.
		
		
			Organizations
		
		
	
- 
		
 - 
		
 - 
		
 - 
		
 - 
		
 - 
		
 - 
		
 - 
		
 - 
		
 - 
		
 - 
		
 
	view article
	
	
		Efficient Request Queueing – Optimizing LLM Performance
			
		   
	
	view article
	
	
		How to generate text: using different decoding methods for language generation with Transformers
			
		   
	
	view article
	
	
		Mixture of Tunable Experts - Behavior Modification of DeepSeek-R1 at Inference Time
			
		By
						
						and 4 others
						•  
				
				•
					
					35