Announcement_15
Our papers “TensorBridge: Bridging Microscaled FP4 Weights to FP8 Tensor Cores for LLM Serving” and “InfiniLoRA: Disaggregated Multi-LoRA Serving for Large Language Models” have been Accepted to ATC 2026.
Our papers “TensorBridge: Bridging Microscaled FP4 Weights to FP8 Tensor Cores for LLM Serving” and “InfiniLoRA: Disaggregated Multi-LoRA Serving for Large Language Models” have been Accepted to ATC 2026.