AI Explained

LongLive-2.0 — NVFP4 W4A4 across training and inference — What does it mean?

NVIDIA's LongLive-2.0 runs training AND inference of a 5B long-video model in NVFP4 — W4A4 matmul plus a 4-bit KV cache — for 2.15× training and 1.84× inference speedup.