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

[misc]: serve the Regenerate-2K examples on TORCH_SDPA and drop narrating comments

Browse Source 
FLASH_ATTN bypassed the cuDNN attention the refine stage selects; TORCH_SDPA keeps it.
This commit is contained in:
Aryan Kumar
2026-10-30 11:35:48 -07:00
parent 39a5679885
commit 01be8e707a
5 changed files with 5 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files
examples/inference/basic/basic_open_h3_regenerate_2k.py
+1 -1
View File
@@ -38,7 +38,7 @@ def parse_args() -> argparse.Namespace:
parser.add_argument("--output", type=Path, default=Path("outputs/open_h3_regenerate_2k"))
parser.add_argument("--steps", type=int, choices=(2, 3), default=3, help="refine steps (3 is the released setting)")
parser.add_argument("--seed", type=int, default=1766580932)
parser.add_argument("--attention-backend", default="FLASH_ATTN")
parser.add_argument("--attention-backend", default="TORCH_SDPA")
parser.add_argument("--draft-size", choices=("768p", "576p"), default="768p",
help="size the draft is encoded at; 576p for drafts from other video models")
parser.add_argument("--runs", type=int, default=1, help="repeat the request to measure warm timings")