⚡Megatron LLM Hub
←Back to search
Twitter

Hedra 在 AMD MI355X 上将 Krea 3 扩散模型推理提速 6.9 倍

推理加速
RT @hedra_labs: We made @krea_ai Krea 3's diffusion transformer 6.9× faster on @AMD Instinct MI355X: 22.9s → 3.3s. Key stats: → 2.8× faster MXFP6 GEMM vs BF16 → 18% → 2% of time waiting on GPU transfers → 98.3% of BF16 quality (SSIM) Here's the work done by the team using our autonomous research system ↓