ポスト
TensorRT 10出たそうです。 これもなあ、 TensorRT-LLM 0.10: Llama3, Phi3, Grok1, and more; FP8 MoEs; improved API simplicity and consolidation TensorRT Model Optimizer 0.11: provides state-of-the-art techniques like quantization and sparsity to reduce model complexity
メニューを開く
