Daniel Maddern
|
1c0883a54b
|
Add persistent hot runtime service
|
2026-08-14 20:13:48 +07:00 |
|
Daniel Maddern
|
a388aa64ff
|
Default video VAE decode to FP16
|
2026-08-14 19:50:36 +07:00 |
|
Daniel Maddern
|
ea7712b4b2
|
Use paired kitchen RoPE in VAE fast path
|
2026-08-14 14:58:11 +07:00 |
|
Daniel Maddern
|
8595dd875e
|
Add optional kitchen VAE fast ops
|
2026-08-14 14:54:38 +07:00 |
|
Daniel Maddern
|
53cd8bd4f4
|
Make runtime diagnostics opt in
|
2026-08-14 14:11:36 +07:00 |
|
Daniel Maddern
|
fea69673cd
|
Return native H3 audio latents
|
2026-08-14 13:57:30 +07:00 |
|
Daniel Maddern
|
59b8302d4e
|
Add direct H3 audio VAE decode
|
2026-08-14 13:39:46 +07:00 |
|
Daniel Maddern
|
b73d08b231
|
Compute upstream VAE temporal overlap constants
|
2026-08-14 13:04:58 +07:00 |
|
Daniel Maddern
|
28a4121df9
|
Match upstream VAE blend implementation
|
2026-08-14 01:41:53 +07:00 |
|
Daniel Maddern
|
49bae4ab74
|
Match upstream VAE temporal padding
|
2026-08-14 01:25:53 +07:00 |
|
Daniel Maddern
|
f85627a9fd
|
Use SageAttention fallback for direct VAE
|
2026-08-14 01:00:16 +07:00 |
|
Daniel Maddern
|
9c9e0857c2
|
Load direct VAE weights as float32
|
2026-08-14 00:52:57 +07:00 |
|
Daniel Maddern
|
e4f145e9d5
|
Mirror upstream VAE block math
|
2026-08-14 00:50:03 +07:00 |
|
Daniel Maddern
|
e043e9af82
|
Use Comfy attention for VAE when available
|
2026-08-14 00:41:20 +07:00 |
|
Daniel Maddern
|
e96af86e72
|
Use fused VAE RMS RoPE when available
|
2026-08-14 00:38:05 +07:00 |
|
Daniel Maddern
|
d45773053e
|
Match upstream H3 VAE temporal decode
|
2026-08-14 00:29:31 +07:00 |
|
Daniel Maddern
|
c3d72d9f1e
|
Timestamp direct memory profile output
|
2026-08-13 23:49:41 +07:00 |
|
Daniel Maddern
|
bc0cff88ce
|
Normalize fastsafetensors CUDA device
|
2026-08-13 23:41:25 +07:00 |
|
Daniel Maddern
|
8ed9eecf17
|
Add fastsafetensors loader option
|
2026-08-13 23:35:01 +07:00 |
|
Daniel Maddern
|
ce022f06e9
|
Add direct mmap and memory profiling controls
|
2026-08-13 23:31:30 +07:00 |
|
Daniel Maddern
|
4018fbea15
|
Match Comfy flow model sigma round trip
|
2026-08-13 22:36:58 +07:00 |
|
Daniel Maddern
|
9d55aef8a6
|
Add H3 free-run parity comparator
|
2026-08-13 22:18:13 +07:00 |
|
Daniel Maddern
|
d0f4dd0ebc
|
Match Comfy H3 timestep precision
|
2026-08-13 21:50:53 +07:00 |
|
Daniel Maddern
|
c4d64d0d72
|
Match Comfy BF16 audio carry input
|
2026-08-13 21:47:02 +07:00 |
|
Daniel Maddern
|
3e56fbc32c
|
Match Comfy BF16 latent packing
|
2026-08-13 21:29:52 +07:00 |
|
Daniel Maddern
|
b491589418
|
Use carried audio sampler state directly
|
2026-08-13 21:23:18 +07:00 |
|
Daniel Maddern
|
f5fe966a7e
|
Match Comfy audio sampler boundary
|
2026-08-13 21:11:41 +07:00 |
|
Daniel Maddern
|
a2c49ad93b
|
Match Comfy sampler BF16 output boundary
|
2026-08-13 16:28:51 +07:00 |
|
Daniel Maddern
|
09f5d2ef65
|
Match Comfy joint AV noise initialization
|
2026-08-13 16:12:10 +07:00 |
|
Daniel Maddern
|
210855c625
|
Stream H3 VAE tiled decode canvas
|
2026-08-13 15:53:15 +07:00 |
|
Daniel Maddern
|
985a529fc9
|
Match H3 final output heads
|
2026-08-13 13:09:42 +07:00 |
|
Daniel Maddern
|
a85fe116c1
|
Match H3 final AdaLN bias
|
2026-08-13 12:40:44 +07:00 |
|
Daniel Maddern
|
807b54ca0e
|
Trace H3 final AdaLN parity
|
2026-08-13 02:59:46 +07:00 |
|
Daniel Maddern
|
b69903b7e6
|
Match H3 DiT backbone trace
|
2026-08-13 01:30:32 +07:00 |
|
Daniel Maddern
|
706892d987
|
Match H3 assembled FL2VA input
|
2026-08-13 00:55:58 +07:00 |
|
Daniel Maddern
|
ab10de7521
|
Match Comfy Qwen FP32 projections
|
2026-08-12 23:59:05 +07:00 |
|
Daniel Maddern
|
4050afe662
|
Match Qwen SDPA dispatch
|
2026-08-12 22:28:41 +07:00 |
|
Daniel Maddern
|
e5ffacc625
|
Report direct sampling progress
|
2026-08-12 21:39:31 +07:00 |
|
Daniel Maddern
|
eed3a3d951
|
Add H3 parity diagnostics
|
2026-08-12 21:11:02 +07:00 |
|
Daniel Maddern
|
0cad1dbc31
|
Honor NVFP4 full precision metadata
|
2026-08-12 21:08:25 +07:00 |
|
Daniel Maddern
|
054b8d58a0
|
Cache GB10 SageAttention3 wheel
|
2026-08-12 15:21:03 +07:00 |
|
Daniel Maddern
|
a8df9ef173
|
Keep direct RoPE path self-contained
|
2026-08-12 14:53:25 +07:00 |
|
Daniel Maddern
|
68606e1a30
|
Use packaged Qwen tokenizer assets
|
2026-08-12 14:39:18 +07:00 |
|
Daniel Maddern
|
f90801ea8a
|
Restore local Qwen AutoTokenizer config
|
2026-08-12 14:35:04 +07:00 |
|
Daniel Maddern
|
7e2062ee38
|
Load Qwen tokenizer from local vocab
|
2026-08-12 14:28:41 +07:00 |
|
Daniel Maddern
|
8851873fb0
|
Initial direct H3 runtime
|
2026-08-12 14:12:42 +07:00 |
|