 coderabbitai[bot]andCodeRabbit
|
a56a64b62e
|
fix: apply CodeRabbit auto-fixes
Fixed 1 file(s) based on 1 unresolved review comment.
Co-authored-by: CodeRabbit <noreply@coderabbit.ai>
|
2026-04-15 07:11:31 +00:00 |
|
xmarre
|
9719017900
|
Harden external state refresh and SeedVR2 install
|
2026-04-15 09:00:00 +02:00 |
|
xmarre
|
cbe4825973
|
Harden SeedVR2 external cache binding
|
2026-04-15 08:49:25 +02:00 |
|
xmarre
|
103613ad4f
|
Harden external residency failure handling
|
2026-04-15 08:36:19 +02:00 |
|
xmarre
|
9d714f896c
|
Harden SeedVR2 external residency hooks
|
2026-04-15 08:28:55 +02:00 |
|
xmarre
|
b0a4c6d7a2
|
Integrate SeedVR2 external cache eviction
|
2026-04-15 08:15:10 +02:00 |
|
xmarre
|
5e427f4196
|
Revise README for clarity and detail enhancement
|
2026-04-15 07:43:04 +02:00 |
|
xmarre
|
e7e4df92bf
|
Merge pull request #11 from xmarre/codex/fix-sticky-vae-headroom
[codex] Preserve sticky VAE headroom
|
2026-04-15 07:08:58 +02:00 |
|
xmarre
|
a7dc557376
|
Preserve sticky VAE headroom
|
2026-04-15 07:03:35 +02:00 |
|
xmarre
|
3f1d995138
|
Merge pull request #10 from xmarre/codex/fix-face-detailer-vram-overflow
[codex] Fix sticky reclaim before Face Detailer VAE encode
|
2026-04-15 06:15:52 +02:00 |
|
xmarre
|
3bbc263a46
|
Fix sticky VRAM reclaim before VAE encode
|
2026-04-15 06:09:41 +02:00 |
|
xmarre
|
2dc41ab929
|
Merge pull request #9 from xmarre/codex/pr8-clone-conflict-unload
[codex] Fix clone-conflict VRAM reclamation
|
2026-04-15 05:30:11 +02:00 |
|
xmarre
|
7dd33f3675
|
Address PR review feedback
|
2026-04-15 05:25:27 +02:00 |
|
xmarre
|
4f36431bf2
|
Fix clone-conflict VRAM reclamation
|
2026-04-15 05:10:51 +02:00 |
|
xmarre
|
8716f77749
|
Merge pull request #8 from xmarre/codex/fix-same-device-vram-eviction
[codex] Fix same-device VRAM eviction
|
2026-04-15 04:07:02 +02:00 |
|
xmarre
|
420b27ba4f
|
Fix same-device VRAM eviction
|
2026-04-15 04:01:28 +02:00 |
|
xmarre
|
342b80d0ec
|
Merge pull request #7 from xmarre/codex/adaptive-resident-trim
Move VRAM trimming into the resident loader path
|
2026-04-15 03:21:32 +02:00 |
|
xmarre
|
fcd4d80f7b
|
Fallback when selected safetensors keys miss
|
2026-04-15 03:14:13 +02:00 |
|
xmarre
|
59ac769635
|
Treat empty component maps as unknown size
|
2026-04-15 03:09:04 +02:00 |
|
xmarre
|
c121278c65
|
Thread adaptive trim to the target CUDA device
|
2026-04-15 03:05:32 +02:00 |
|
xmarre
|
da3f105661
|
Move VRAM trimming into resident loaders
|
2026-04-15 02:57:40 +02:00 |
|
xmarre
|
1365161b49
|
Merge pull request #6 from xmarre/codex/resident-loader-two-fixes
Add selective checkpoint ingest and resident VRAM trim
|
2026-04-15 02:38:56 +02:00 |
|
xmarre
|
cfb707f082
|
Fix residency entry lookup locking
|
2026-04-15 02:36:35 +02:00 |
|
xmarre
|
19e69a8ecc
|
Address PR review comments
|
2026-04-15 02:29:52 +02:00 |
|
xmarre
|
f7b8fe5cc9
|
Add selective checkpoint ingest and resident VRAM trim
|
2026-04-15 02:17:16 +02:00 |
|
xmarre
|
2643a1903b
|
Merge pull request #5 from xmarre/codex/narrow-resident-loader-hot-path
[codex] Narrow resident loader hot paths
|
2026-04-13 06:28:08 +02:00 |
|
xmarre
|
d11d8e0a25
|
Fix loader-keyed load report attribution
|
2026-04-13 06:24:27 +02:00 |
|
xmarre
|
df9128e9ee
|
Fix resident loader reuse edge cases
|
2026-04-13 06:16:06 +02:00 |
|
xmarre
|
9f4b27eb23
|
Narrow resident loader hot paths
|
2026-04-13 06:00:19 +02:00 |
|
xmarre
|
b94fd0b3f3
|
Merge pull request #4 from xmarre/codex/fix-loader-extra-unet-filter
Filter extra diffusion loader state dicts to UNet keys
|
2026-04-12 10:39:55 +02:00 |
|
xmarre
|
1b80a6a82b
|
Preserve sparse extra UNet overrides
|
2026-04-12 10:36:40 +02:00 |
|
xmarre
|
6d4bd6c7c4
|
Filter extra diffusion weights to UNet keys
|
2026-04-12 10:24:59 +02:00 |
|
xmarre
|
d533beb275
|
Merge pull request #3 from xmarre/codex/policy-override-loader
Add explicit residency policy loader input
|
2026-04-12 06:49:22 +02:00 |
|
xmarre
|
24ab29880a
|
Scope loader policy override to load
|
2026-04-12 06:45:32 +02:00 |
|
xmarre
|
791a48afd3
|
Add explicit residency policy loader input
|
2026-04-12 06:35:30 +02:00 |
|
xmarre
|
1253b88361
|
Merge pull request #2 from xmarre/codex/fix-clip-metadata-cpu
[codex] Keep CLIP metadata tensors on CPU
|
2026-04-12 05:55:53 +02:00 |
|
xmarre
|
ca8118de03
|
fix cpu fallback and torch remap handling
|
2026-04-12 05:54:14 +02:00 |
|
xmarre
|
752def584f
|
load torch checkpoints on cpu before cuda remap
|
2026-04-12 05:42:29 +02:00 |
|
xmarre
|
871c144ac9
|
keep clip metadata tensors on cpu
|
2026-04-12 05:26:51 +02:00 |
|
xmarre
|
ca0d55ce04
|
Merge pull request #1 from xmarre/codex/import-zip-implementation
[codex] Import GPU resident loader implementation
|
2026-04-12 04:52:39 +02:00 |
|
xmarre
|
ffe93ec16d
|
Fix telemetry and weakref entry lookup
|
2026-04-12 04:45:43 +02:00 |
|
xmarre
|
a2bff64207
|
Fix loader state restoration and residency bookkeeping
|
2026-04-12 04:35:13 +02:00 |
|
xmarre
|
669e6014fd
|
Fix package imports and patch guards
|
2026-04-12 04:14:07 +02:00 |
|
xmarre
|
d0fe3f5058
|
Import GPU resident loader implementation
|
2026-04-12 03:46:23 +02:00 |
|
xmarre
|
08387e2636
|
Initial commit
|
2026-04-12 03:33:01 +02:00 |
|