 H1yori233
|
9f94673c34
|
fix
|
2026-08-06 21:13:14 -07:00 |
|
|
H1yori233
|
c150889330
|
update server
|
2026-08-06 20:47:35 -07:00 |
|
|
H1yori233
|
7f783e30b7
|
add inference script
|
2026-08-06 18:18:36 -07:00 |
|
|
lpc0220
|
ec9db97431
|
[kernel] attention: sm_100a CUDA forward for block-causal-sink (Blackwell) (#1677)
|
2026-08-06 16:36:47 -07:00 |
|
|
H1yori233
|
fd236a06a7
|
add config
|
2026-07-24 20:29:03 -07:00 |
|
|
H1yori233
|
54fe0be488
|
app test
|
2026-07-24 20:04:31 -07:00 |
|
|
H1yori233
|
3a398a2bbd
|
[bugfix]: load only exported role from DCP
|
2026-07-24 08:44:33 -07:00 |
|
|
H1yori233
|
4e76897f1f
|
[bugfix]: restore lazy optimizer checkpoints
|
2026-07-23 12:19:14 -07:00 |
|
|
H1yori233
|
95d8e74d65
|
[bugfix]: flatten WanTrack validation logging
|
2026-07-23 11:37:43 -07:00 |
|
|
H1yori233
|
bcd0ad7dee
|
[bugfix]: preserve WanTrack sampling dtype
|
2026-07-23 03:05:32 -07:00 |
|
|
H1yori233
|
9acbf92455
|
[bugfix]: support leading I2V frame in WanTrack sampling
|
2026-07-23 02:59:46 -07:00 |
|
|
H1yori233
|
ce4fa8ef2d
|
[feat]: add bidirectional and causal WanTrack support
|
2026-07-23 02:23:10 -07:00 |
|
|
H1yori233
|
41dcd065ae
|
Fix rank-local dataloader checkpoint resume
|
2026-07-22 21:29:48 -07:00 |
|
|
H1yori233
|
c0cb2228ac
|
Fix causal EMA update and export semantics
|
2026-07-22 21:29:48 -07:00 |
|
|
H1yori233
|
2fa0f70ee8
|
Use 21 latent frames for OpenVid causal training
|
2026-07-22 21:29:47 -07:00 |
|
|
H1yori233
|
e172215880
|
Harden OpenVid launcher modes
|
2026-07-22 21:29:46 -07:00 |
|
|
H1yori233
|
23e3b325a4
|
harden-openvid-launch-safety
|
2026-07-22 21:29:46 -07:00 |
|
|
H1yori233
|
44d0990199
|
streaming-config-parser
|
2026-07-22 21:29:45 -07:00 |
|
|
H1yori233
|
59b6578906
|
feat: add OpenVid causal A12-A15 runs
|
2026-07-22 21:29:45 -07:00 |
|
|
H1yori233
|
fd8372d172
|
Add OpenVid causal A12-A15 experiment plan
|
2026-07-22 21:29:44 -07:00 |
|
|
H1yori233
|
33eb7ea13c
|
feat(dataset): harden parquet streaming loader
|
2026-07-22 21:29:43 -07:00 |
|
|
H1yori233
|
051d21958d
|
[feat]:
|
2026-07-22 21:29:43 -07:00 |
|
|
H1yori233
|
bf29e20bf5
|
[bugfix]: fix causal Wan batch and padding dimensions
|
2026-07-22 21:29:42 -07:00 |
|
|
H1yori233
|
291fa5d9a6
|
fix(train): save and export exact EMA checkpoints
|
2026-07-22 21:29:42 -07:00 |
|
|
H1yori233
|
954daf7fb3
|
Add
|
2026-07-22 21:29:40 -07:00 |
|
|
H1yori233
|
e05c04a2f6
|
[feat]: import block causal sink attention kernel
|
2026-07-22 21:29:05 -07:00 |
|
|
pkisfaludi-nvandClaude Opus 4.8
|
9fb74b9732
|
Make LTX-2 RMSNorm out-of-place so torch_tensorrt + Ulysses SP compiles (#1623)
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
|
2026-07-22 04:32:04 -07:00 |
|
|
Adriel FungandSolitaryThinker
|
521dee0e82
|
[perf]: enable per-block torch.compile for LTX2 with persistent cache (#1602)
Co-authored-by: SolitaryThinker <wlsaidhi@gmail.com>
|
2026-07-20 15:59:13 -07:00 |
|
|
William Lin
|
229419208e
|
[ci]: opt in to fork-PR head checkout after actions/checkout guard change (#1625)
|
2026-07-20 13:12:22 -07:00 |
|
|
William Lin
|
65f3b946b9
|
[feat] Add LTX-2 and LTX-2.3 fine-tuning to the modular trainer (#1624)
|
2026-07-20 11:58:39 -07:00 |
|
|
Zhang Peiyuan
|
191fcbf46c
|
[feat] add qat docs (#1621)
|
2026-07-19 18:37:47 -07:00 |
|
|
Junda Su
|
755a4e4470
|
[new-model] Add LingBot-Video Dense and MoE/refiner T2V inference (#1595)
|
2026-07-18 20:18:16 -07:00 |
|
|
|
9709b7513b
|
[feat] Port NVFP4 QAT/QAD to modular train framework (#1619)
Co-authored-by: Peiyuan Zhang <email>
Co-authored-by: Peiyuan <a>
|
2026-07-18 15:01:09 -07:00 |
|
|
William Lin
|
32cd603515
|
Revert docs trusted-branch-only workflow (#1618)
|
2026-07-17 00:22:56 -07:00 |
|
|
Junda Su
|
d4bdd3621a
|
[new-model] Port LingBot-World-v2 (#1579)
|
2026-07-16 19:51:53 -07:00 |
|
|
William Lin
|
e2f8322842
|
[ci]: skip unused Buildkite submodule checkout (#1614)
|
2026-07-16 18:37:57 -07:00 |
|
|
|
6966f9e0bc
|
[fix] Z-Image (#1236) draft port: rebase + strict-load contract + bf16 encoder parity + PORT_STATUS (#1339)
Co-authored-by: Mrinaal Dogra <mdogra@ucsd.edu>
Co-authored-by: SolitaryThinker <wlsaidhi@gmail.com>
|
2026-07-16 18:18:25 -07:00 |
|
|
Mac Lee
|
743f4ed5f9
|
[ci]: harden Modal repository checkout (#1590)
|
2026-07-16 18:05:50 -07:00 |
|
|
Mac Lee
|
1c04ace573
|
[ci]: pin VSA training regression to H100 (#1591)
|
2026-07-15 22:04:57 -07:00 |
|
|
Mac LeeandSatyam Srivastava
|
6cbff73687
|
[bugfix]: skip unused output materialization (#1567)
Co-authored-by: Satyam Srivastava <srivastavasatyam53@gmail.com>
|
2026-07-16 04:03:07 +00:00 |
|
|
William Lin
|
dec8b10939
|
[docs]: document automatic Docker image builds (#1608)
|
2026-07-15 18:52:21 -07:00 |
|
|
William Lin
|
133a5278af
|
[ci] Run docs only for trusted PR branches (#1610)
|
2026-07-15 18:51:59 -07:00 |
|
|
William Lin
|
da856274cc
|
[feat]: FastVideo Studio — SvelteKit → Next.js port + review fixes (#1612)
|
2026-07-15 18:51:33 -07:00 |
|
|
Mac LeeandSolitaryThinker
|
a253856147
|
[ci] Add exact identity performance statuses (#1560)
Co-authored-by: SolitaryThinker <wlsaidhi@gmail.com>
|
2026-07-15 14:59:09 -07:00 |
|
|
Satyam Srivastavaandgemini-code-assist[bot]
|
6e25d94ebc
|
[ci]: enable scheduled perf runs to update rolling baseline (#1599)
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
|
2026-07-14 16:55:12 -07:00 |
|
|
Mac Lee
|
cae8fa18dc
|
[bugfix]: propagate Qwen2.5-VL visual dtype (#1580)
|
2026-07-13 18:37:11 -07:00 |
|
|
William Lin
|
821e5a0832
|
[bugfix]: fix FlashAttention resolver tests after tuple return (#1597)
|
2026-07-13 16:29:03 -07:00 |
|
|
William Lin
|
c1abc42782
|
[bugfix]: allow unrestricted head sizes in SDPA (#1596)
|
2026-07-13 16:04:51 -07:00 |
|
|
William Lin
|
ef15ea2391
|
[bugfix]: keep LTX2 rms_norm outputs bf16 under torch 2.12 autocast (#1587)
|
2026-07-13 16:04:21 -07:00 |
|
|
Mac Lee
|
1ea2517e22
|
[ci]: extend LoRA training CI timeout (#1589)
|
2026-07-13 02:47:28 -07:00 |
|