SolitaryThinker
423f8d7eff
[misc] cosmos3 PORT_STATUS: framework-reference pivot + Phase 1 findings
2026-07-20 12:19:17 -07:00
SolitaryThinker
a91482ed14
[feat] cosmos3: arch config 1:1 with Cosmos3-Nano checkpoint
2026-07-20 12:19:17 -07:00
SolitaryThinker
f0c838a78d
[misc]: cosmos3 PORT_STATUS: post-rebase state + fv-cosmos3 env
2026-07-20 12:19:17 -07:00
SolitaryThinker
13c76b710b
[misc]: cosmos3 resume: PORT_STATUS + README for official diffusers ref
2026-07-20 12:19:17 -07:00
SolitaryThinker
4bd3eff562
[feat]: Cosmos3 checkpoint conversion script (cosmos3_convert.py)
...
scripts/checkpoint_conversion/cosmos3_convert.py wraps Cosmos3OmniDiffusersPipeline._remap_ckpt_key. convert_state_dict(src) returns (new_state, skipped, unmapped) for shard-by-shard remap; convert_checkpoint_dir reads *.safetensors shards and writes a consolidated FastVideo-format state dict (sharded index.json TODO when real weights land). smoke_test() exercises all 14 representative remap branches synthetically (no real weights needed) and returns nonzero exit on failure; runs in CI as a remap-drift guard. Usage: python scripts/checkpoint_conversion/cosmos3_convert.py --smoke-test.
2026-07-20 12:19:17 -07:00
SolitaryThinker
041e21821a
[feat]: Cosmos3Config + registry wire-up for nvidia/Cosmos3-Nano
...
Cosmos3Config(PipelineConfig): reuses Cosmos25VAEConfig (Cosmos3 uses DistributedAutoencoderKLWan); text_encoder_configs=() since Cosmos3LanguageModel lives inside the DiT; flow_shift=1.0 default (T2V/I2V engine init; T2I uses 3.0 per-request via _set_flow_shift). Registry entry registers BEFORE the generic cosmos detector to win path precedence (same pattern as GEN3C). Resolves nvidia/Cosmos3-Nano -> Cosmos3Config without regressing Cosmos25/GEN3C/Cosmos.
2026-07-20 12:19:17 -07:00
SolitaryThinker
d254b7455d
[feat]: Cosmos3 pipeline (Cosmos3OmniDiffusersPipeline)
...
Pipeline class with: _remap_ckpt_key static method (verbatim port from pipeline_cosmos3.py:319-409, 14-rule checkpoint remap UND/GEN split + lm_head skip); _set_flow_shift method with lazy UniPCMultistepScheduler construction; diffuse() with sequential 3-mode CFG denoising loop + I2V velocity_mask + image_latent re-injection (ported from pipeline_cosmos3.py:883-1033); forward() with T2I/T2V/I2V mode dispatch + flow_shift selection (ported from pipeline_cosmos3.py:1037-1206); 4 helper-method stubs raise NotImplementedError. Dual inheritance (nn.Module, ComposedPipelineBase) matches upstream pattern.
2026-07-20 12:18:53 -07:00
SolitaryThinker
b0f1b8ad96
[feat]: Cosmos3 DiT skeleton (Cosmos3VFMTransformer + Cosmos3LanguageModel)
...
Ports math (compute_mrope_position_ids_text/_vision, patchify, unpatchify) verbatim from vllm-omni transformer_cosmos3.py:113-177,1009-1036. Module tree (language_model.layers.*.self_attn.{q,k,v,o}_proj + gen_layers.*.cross_attention.* + vae2llm + llm2vae + time_embedder + norm_moe_gen) exposes the parameter names the checkpoint converter targets. All layer forward() raise NotImplementedError until weights publish; module instantiation + state-dict key tests pass.
2026-07-20 12:18:53 -07:00
SolitaryThinker
5d778c94a1
[test]: Cosmos3 local-test parity scaffold (Tier A, 15 tests)
...
Adds 8 CPU-only parity test files + conftest stubs (StubScheduler, StubCosmos3VAE, StubCosmos3Transformer) under tests/local_tests/cosmos3/ mirroring the vllm-omni reference at tests/diffusion/models/cosmos3/conftest.py. All 15 tests skip until the FastVideo modules land (subsequent commits). Reference: vllm-omni PR #3454 @ 8536f5b1421f.
2026-07-20 12:18:53 -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 Lee and Satyam 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 Lee and SolitaryThinker
a253856147
[ci] Add exact identity performance statuses ( #1560 )
...
Co-authored-by: SolitaryThinker <wlsaidhi@gmail.com >
2026-07-15 14:59:09 -07:00
Satyam Srivastava and gemini-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
Mook and SolitaryThinker
0c63528c59
[perf] Cache RoPE position-embedding tables across denoising steps ( #1442 )
...
Co-authored-by: SolitaryThinker <wlsaidhi@gmail.com >
2026-07-13 02:34:51 -07:00
b063f8ca41
[feat] Fix FLUX.1-dev port: native RoPE, parity tests, SSIM reference ( #1321 )
...
Co-authored-by: Ishan Vaish <ivaish@ucsd.edu >
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com >
2026-07-13 01:49:42 -07:00
William Lin
e7fff0173a
[bugfix]: benchmark_weight_loading_comparison.py — iterate safe_open via .keys() ( #1378 )
2026-07-12 22:50:45 -07:00
Shreejith SG and H1yori233
d82abc271e
[feat] Add GLM-Image inference support ( #1030 )
...
Co-authored-by: H1yori233 <k1kong@ucsd.edu >
2026-07-12 22:42:42 -07:00
Guian Fang and SolitaryThinker
970409962f
[feat] Add AnyFlow any-step video distillation (pretrain + on-policy) ( #1371 )
...
Co-authored-by: SolitaryThinker <wlsaidhi@gmail.com >
2026-07-12 02:32:08 +00:00
Raghav K
055586703d
[perf]: register a real backward for FA2 default + masked/varlen custom ops (training-under-compile) ( #1388 )
2026-07-12 00:45:27 +00:00
Mac Lee
5d89f86675
[ci] Stop forcing FA4 in model-load lanes ( #1561 )
2026-07-11 14:10:36 -07:00
Satyam Srivastava
19a51a1fe6
[ci] Trigger performance benchmarks for performance code changes ( #1583 )
2026-07-10 20:21:33 -07:00
William Lin
d3232cea5a
[ci]: gate the full-suite trigger on pre-commit and docs build ( #1572 )
2026-07-11 02:56:49 +00:00
Raghav K and SolitaryThinker
0c90c8c24d
[bugfix] nvfp4: cast fp32 inputs to bf16 instead of asserting ( #1488 )
...
Co-authored-by: SolitaryThinker <wlsaidhi@gmail.com >
2026-07-10 21:39:17 +00:00
Mingjia Huo and Claude Fable 5
4c08ffce49
[feat] World model training using third person games ( #1443 )
...
Co-authored-by: Claude Fable 5 <noreply@anthropic.com >
2026-07-10 05:09:07 +00:00
Atharv Ramesh
af4a77553c
[ci]: add SSIM reference bootstrap flow ( #1522 ) ( #1547 )
2026-07-10 01:49:38 +00:00
alexzms and SolitaryThinker
c096fda1eb
[docs] Add LTX-2.3 distilled inference run configs (t2v/i2v × 5+2/8+3 × resolutions) ( #1568 )
...
Co-authored-by: SolitaryThinker <wlsaidhi@gmail.com >
2026-07-09 18:53:12 +00:00
William Lin
8f47e85be0
[bugfix]: retry remote image downloads in load_image ( #1570 )
2026-07-09 07:33:24 -07:00
William Lin
90d3bd19eb
[infra] Deliver per-job Buildkite env to Modal CI at runtime, not as image layers ( #1569 )
2026-07-09 06:33:37 -07:00
Mac Lee and SolitaryThinker
afb4f7d3c5
[ci]: emit v2 performance result schema ( #1551 )
...
Co-authored-by: SolitaryThinker <wlsaidhi@gmail.com >
2026-07-09 06:11:15 +00:00
02e1143f22
[feat] Add Kandinsky-5 T2V/I2V pipeline support ( #1471 )
...
Co-authored-by: Aryan Kumar <aryan5v@users.noreply.github.com >
Co-authored-by: leffff <levnovitskiy@gmail.com >
Co-authored-by: SolitaryThinker <wlsaidhi@gmail.com >
2026-07-07 14:43:30 -07:00
Kared and SolitaryThinker
e2f4d1a7b5
[feat]: add SwanLab tracker ( #1461 )
...
Co-authored-by: SolitaryThinker <wlsaidhi@gmail.com >
2026-07-07 08:35:38 +00:00
Kaiqin Kong and SolitaryThinker
f037351146
[feat] Add Clean-history Teacher Forcing and Causal Consistency Distillation ( #1505 )
...
Co-authored-by: SolitaryThinker <wlsaidhi@gmail.com >
2026-07-07 08:13:11 +00:00
Mac Lee and SolitaryThinker
1ee11e08dc
[ci]: add performance fingerprint cohorts ( #1546 )
...
Co-authored-by: SolitaryThinker <wlsaidhi@gmail.com >
2026-07-07 07:24:00 +00:00
SolitaryThinker