Robuta

https://predibase.com/blog/turbo-lora Turbo LoRA: 2-3x faster fine-tuned LLM inference Turbo LoRA is a new parameter-efficient fine-tuning method we’ve developed at Predibase that increases text generation throughput by 2-3x while... turbo lorafaster finetunedllm https://wavespeed.ai/models/wavespeed-ai/z-image/turbo-lora Z-Image-Turbo LoRA | Text-to-Image by Tongyi-MAI | WaveSpeedAI Z-Image-Turbo LoRA (6B) enables ultra-fast text-to-image generation with external LoRA support. Generate photorealistic images in sub-second latency while... z image turbolora texttongyi