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

Record sampler wrapper boundary fix

Browse source
This commit is contained in:
Daniel Maddern 2026-08-13 16:57:44 +07:00
parent a2c49ad93b
commit b24ffe67a2
1 changed files with 5 additions and 5 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

10
PARITY.md
View file

@ -189,7 +189,7 @@ gate and is exact.
| Beta/RES sampler | Yes | H3 replay is bit-exact for all 12 captured sampler calls and RES update is bit-exact from captured denoised; direct raw-output to model-wrapper denoised conversion retains small BF16/state boundary deltas |
| Video VAE decoder | Yes | Same final sampled latent decoded through direct VAE versus Comfy PNG frames: mean abs pixel delta `0.0833898`, max `6` |
| Audio VAE/decode/mux | No | Preview intentionally produces video only |
| End-to-end prompt-only FL2VA preview | Yes | Direct 320x192x22 dragon smoke videos generated with Sage2. Comfy-equivalent CPU joint AV seed initialization now matches captured `initial.pt` exactly; seed-exact direct MP4 versus Comfy PNG frames still has mean abs pixel delta `14.0714`, max `193`, consistent with the remaining model-wrapper denoised conversion boundary |
| End-to-end prompt-only FL2VA preview | Yes | Direct 320x192x22 dragon smoke videos generated with Sage2. Comfy-equivalent CPU joint AV seed initialization matches captured `initial.pt` exactly. Video-side wrapper denoised conversion is exact after BF16 raw-output materialization; remaining seed-exact final-latent delta is localized to regenerated text conditioning plus audio-side wrapper conversion |
| Full Ref2VA | No | References, vision conditioning, VAE encode, audio, and muxing are unimplemented |
## Remaining Gates, In Dependency Order
@ -199,10 +199,10 @@ unless the checkpoint, Comfy version, prompt, or backend changes.
1. **Final video latent layout.** Compare direct `unpatchify_video` output
with Comfy before entering the sampler.
2. **Model-wrapper denoised conversion.** Direct H3 and RES update gates pass,
and direct initial AV noise now matches Comfy exactly. Close the remaining
small `h3_output -> denoised` conversion delta before claiming identical
seed output.
2. **Text/audio end-to-end closure.** Direct H3, video wrapper conversion,
RES update, VAE decode, and initial AV noise now match their captures.
Close regenerated text conditioning and audio-side wrapper conversion before
claiming identical seed output.
3. **Feature/performance work.** Only then add audio, Ref2VA/reference paths,
Sage3, CUDA graphs, and multi-GPU execution.