QLoRA

Posts in tags: "QLoRA" (2 posts)

May 09, 2026

Research

Speculative Decoding for Free: Pairing DFlash with our DFO-Tuned Gemma 4 31B

z-lab's DFlash drafter on our QLoRA fine-tune captured 92% of the published speedup with no retraining. ~15x faster, ~4x cheaper in prod.

DFlashSpeculative DecodingGemma 4vLLMInferenceH100QLoRADFO

April 26, 2026

Research

A 200-item RAG arena tied at the mean, but two LLM judges only agreed at Spearman ρ=0.55. They aren't measuring the same thing.

RAG-ArenaScoredQARAG RoutingEXITLLM-as-JudgeSpearmanEvaluationQLoRA