Davide Locatelli
e1e2559359
These speed-ups for the MiniMax-H3 pipelines keep the output bit-identical. Each one has a switch that is off by default: - FASTVIDEO_MINIMAX_H3_EXACT_KERNELS: Triton RoPE, AdaLN modulation, gated residual and SwiGLU kernels that round to bf16 at the same points as the eager ops. - FASTVIDEO_H3_VSA_HEADS_FIRST_TILE: VSA-H3 tiles are written directly in the heads-first layout of the kernel. - FASTVIDEO_H3_VAE_TILE_PARALLEL: VAE spatial tiles are split across the sequence-parallel ranks. - FASTVIDEO_H3_REF2VA_MEMO_ENTRIES: repeat reference encodes are reused. The example basic_fasth3_omniref_pdd.py --lossless-accel turns them all on. On GB200 with 4 GPUs, MiniMax-H3 text to video with audio (124 frames, 1344x768) gives bit-identical frames and audio with the first three switches on and off.
11 lines
436 B
JSON
11 lines
436 B
JSON
{
|
|
"name": "speaker",
|
|
"prompt": "Picture 1 walks slowly toward the camera across the living room, smiling, and says, \"Every detail was chosen with care.\" Smooth tracking shot, warm afternoon light, light footsteps on the wooden floor.",
|
|
"reference": "speaker.png",
|
|
"reference_sha256": "d38ba6675b5c780be57818aea0109a8f028d09268c3f29bf00f2739167a6c92c",
|
|
"seed": 413410,
|
|
"height": 768,
|
|
"width": 1344,
|
|
"num_frames": 124
|
|
}
|