daniel/h3-blackwell-runtime
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Match Comfy BF16 latent packing

Browse source
This commit is contained in:
Daniel Maddern 2026-08-13 21:29:52 +07:00
parent b491589418
commit 3e56fbc32c
1 changed files with 2 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
src/h3_blackwell_runtime/packing.py
View file

@ -72,8 +72,8 @@ class H3PromptPacker:
text_rows = text[0].to(torch.bfloat16)
else:
raise ValueError("H3 text states must be Qwen 5120-wide or refined 5376-wide.")
video_rows = functional.linear(patchify_video(video).float(), self.video_weight, self.video_bias).to(torch.bfloat16)
audio_rows = functional.linear(pack_audio(audio).float(), self.audio_weight, self.audio_bias).to(torch.bfloat16)
video_rows = functional.linear(patchify_video(video.to(torch.bfloat16)).float(), self.video_weight, self.video_bias).to(torch.bfloat16)
audio_rows = functional.linear(pack_audio(audio.to(torch.bfloat16)).float(), self.audio_weight, self.audio_bias).to(torch.bfloat16)
text_length, audio_length = text_rows.shape[0], audio_rows.shape[0]
hidden = torch.cat((text_rows, audio_rows, video_rows))
video_sigma = torch.tensor(float(sigma), device=hidden.device).clamp(min=1e-6)