Will LinandClaude Fable 5
0a861031c7
With enable_torch_compile_vae (#1734, opt-in) inductor autotunes kernels per process, so chunk decodes on other ranks differ from the serial rank's decode the way two serial processes differ (GB200 @124f: max 63/255 on <0.5% of pixels, mean ~1e-2/255; audio and chunk 0 bit-identical). Eager decoder (the default) stays bitwise-equal to serial decode_to_pixels - measured, both strategies, x3, 124f+345f. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>