ReadQrita: High-performance Top-k and Top-p Algorithm for GPUs using Pivot-based Truncation and Selection#GPU optimization#LLM optimizationarXiv: Artificial IntelligencearticleNov 4, 2026
ReadTemperature, Not Knowledge: What Recursive Self-Training and Its Remedies Do to a Language Model's Confidence#Uncertainty quantification LLMs#LLM TechniquesarXiv: Artificial IntelligencearticleNov 3, 2026
Large Language ModelReadFirst Token Cutoff LLM sampling#Large Language Model#Language modelsAntireztutorialJan 12, 2024