DeepHub IMBA

Oct 19, 2026 · Artificial Intelligence

vLLM 0.32.0: Segmented Attention & W4A16 Speed Up Ryzen AI MAX+ 395

vLLM 0.32.0 introduces ROCm Segmented Attention backend and W4A16 kernel optimizations for AMD Ryzen AI MAX+ 395 (gfx1151), delivering up to 2.5x attention throughput and 22% TTFT reduction, though FP8 support remains limited without native hardware acceleration.