nodes/hao-ai-lab-FastVideo
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

[docs] Pika H3 Flex cookbook: --weights for the NVFP4 QAD releases and FP4 attention (#2054)

Browse Source 
Co-authored-by: Aryan Kumar <aryan5v@users.noreply.github.com>
This commit is contained in:
Aryan Kumar
2026-11-03 01:07:54 -08:00
committed by GitHub
co-authored by Aryan Kumar
parent 4b4df1a94e
commit 661d18ba55
2 changed files with 55 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files
examples/inference/basic/basic_pika_h3_flex.py
+29 -4
View File
@@ -14,7 +14,8 @@ does not expose a step-count flag. ``--lossless-accel`` turns on the existing
training-free FastVideo switches (bit-identical kernels, reference memo,
parallel VAE tiles) before the generator starts. ``--nvfp4-decoder`` and
``--nvfp4-text-encoder`` opt into the existing Blackwell FP4 weight paths;
``--nvfp4-dit h3_dit`` loads a packed NVFP4 DiT export (e.g.
``--weights nvfp4-qad`` (or ``nvfp4-qad-fp4-attention``) selects FastVideo's NVFP4 QAD release;
``--nvfp4-dit h3_dit`` loads any packed NVFP4 DiT export (e.g.
FastVideo/Pika-H3-Flex-NVFP4-QAD). They change weights, not the six-forward sampler. Kernel/VSA work is separate.
``--nvfp4-attention`` turns on FlashAttention-4 NVFP4 attention (Q/K in NVFP4, P/V in BF16; Blackwell and FA4 only)
@@ -104,9 +105,31 @@ def _reference(value: str) -> MiniMaxH3Reference:
return MiniMaxH3Reference(source=source, media_type=media_type)
WEIGHT_PRESETS = {
"bf16": {
"model_path": "Pika-Labs/Pika-H3-Flex"
},
"nvfp4-qad": {
"model_path": "FastVideo/Pika-H3-Flex-NVFP4-QAD",
"nvfp4_dit": "h3_dit"
},
"nvfp4-qad-fp4-attention": {
"model_path": "FastVideo/Pika-H3-Flex-NVFP4-FP4Attn-QAD",
"nvfp4_dit": "h3_dit",
"nvfp4_attention": "smooth_k+hadamard",
"nvfp4_attention_bf16_blocks": "45,49"
},
}
def parse_args() -> argparse.Namespace:
parser = argparse.ArgumentParser(description=__doc__, formatter_class=argparse.RawDescriptionHelpFormatter)
parser.add_argument("--model-path", default="Pika-Labs/Pika-H3-Flex")
parser.add_argument("--weights",
choices=tuple(WEIGHT_PRESETS),
default="bf16",
help="bf16: Pika's release; nvfp4-qad: FastVideo's NVFP4 QAD release; "
"nvfp4-qad-fp4-attention: NVFP4 QAD with FP4 attention (both need Blackwell)")
parser.add_argument("--model-path", help="local model directory or Hub repo (overrides --weights)")
parser.add_argument("--task", choices=TASKS, default="t2va")
parser.add_argument("--prompt", required=True)
parser.add_argument("--image", help="first frame (i2va/fl2va)")
@@ -146,10 +169,12 @@ def parse_args() -> argparse.Namespace:
choices=tuple(QK_TRANSFORMS),
help="FA4 NVFP4 Q/K attention with this exact Q/K preconditioning (default: BF16 attention)")
parser.add_argument("--nvfp4-attention-bf16-blocks",
default="",
help="comma-separated transformer_blocks indices that keep BF16 attention, e.g. 45,49")
parser.add_argument("--output", default="outputs/pika_h3_flex")
args = parser.parse_args()
for name, value in WEIGHT_PRESETS[args.weights].items():
if getattr(args, name) is None:
setattr(args, name, value)
if args.nvfp4_attention_bf16_blocks and not args.nvfp4_attention:
parser.error("--nvfp4-attention-bf16-blocks needs --nvfp4-attention")
try:
@@ -232,7 +257,7 @@ def _apply_nvfp4_attention(args: argparse.Namespace) -> None:
return
envs.FASTVIDEO_NVFP4_FA4.set(True)
envs.FASTVIDEO_NVFP4_FA4_QK_TRANSFORM.set(args.nvfp4_attention)
envs.FASTVIDEO_NVFP4_FA4_BF16_BLOCKS.set(args.nvfp4_attention_bf16_blocks)
envs.FASTVIDEO_NVFP4_FA4_BF16_BLOCKS.set(args.nvfp4_attention_bf16_blocks or "")
envs.setdefault_external("CUTE_DSL_ENABLE_TVM_FFI", "1")