SolitaryThinker
df8990807a
[misc] cosmos3 PORT_STATUS: PR1 video core complete (framework parity)
2026-06-06 23:55:47 -07:00
SolitaryThinker
77bf05b2e8
[feat] cosmos3: native video pipeline + framework denoise parity
2026-06-06 23:54:32 -07:00
SolitaryThinker
3419468923
[feat] cosmos3: native MoT sequence-packing (video) + framework parity
2026-06-06 23:23:31 -07:00
SolitaryThinker
63b705340e
[misc] cosmos3 PORT_STATUS: strict-load done; only pipeline remains
2026-06-06 23:11:36 -07:00
SolitaryThinker
b5a8e0fb61
[feat] cosmos3: strict-load verified (identity; needs_conversion=no)
2026-06-06 23:10:39 -07:00
SolitaryThinker
30a4b61e4f
[misc] cosmos3 PORT_STATUS: VAE component framework parity verified
2026-06-06 22:05:32 -07:00
SolitaryThinker
d16a859cf1
[feat] cosmos3: VAE config (Wan2.2 reuse) + framework parity test
2026-06-06 22:04:25 -07:00
SolitaryThinker
f009bf380a
[misc] cosmos3 PORT_STATUS: DiT framework parity verified (both rope modes)
2026-06-06 21:05:44 -07:00
SolitaryThinker
7c46332955
[test] cosmos3: DiT unified_3d_mrope framework parity (real checkpoint)
2026-06-06 21:04:53 -07:00
SolitaryThinker
59a4a571cc
[feat] cosmos3: native DiT + framework parity (Cosmos3VFMTransformer)
2026-06-06 20:52:36 -07:00
SolitaryThinker
2293d30eb8
[misc] cosmos3 PORT_STATUS: PR1 progress (arch config, framework parity ref)
2026-06-06 20:30:21 -07:00
SolitaryThinker
dd97efda3b
[test] cosmos3: official framework DiT parity reference (CPU/SDPA)
2026-06-06 20:29:08 -07:00
SolitaryThinker
90c63fd0f1
[misc] cosmos3 PORT_STATUS: framework-reference pivot + Phase 1 findings
2026-06-06 20:03:17 -07:00
SolitaryThinker
9567efdf07
[feat] cosmos3: arch config 1:1 with Cosmos3-Nano checkpoint
2026-06-06 20:02:43 -07:00
SolitaryThinker
7cb154337f
[misc]: cosmos3 PORT_STATUS: post-rebase state + fv-cosmos3 env
2026-06-06 19:28:13 -07:00
SolitaryThinker
2274771b4b
[misc]: cosmos3 resume: PORT_STATUS + README for official diffusers ref
2026-06-06 19:23:23 -07:00
SolitaryThinker
31f03df62b
[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.
2026-06-06 19:23:23 -07:00
SolitaryThinker
69587f631e
[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.
2026-06-06 19:23:23 -07:00
SolitaryThinker
0b175e414a
[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.
2026-06-06 19:18:19 -07:00
SolitaryThinker
cc55c10e0a
[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.
2026-06-06 19:18:19 -07:00
SolitaryThinker
c669b2d4b4
[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.
2026-06-06 19:18:19 -07:00
William Lin
1c627a3f98
[bugfix]: build fastvideo-kernel on GPU-less Docker runners ( #1437 )
2026-06-06 17:52:45 -07:00
Kaiqin Kong
a931efe33a
[bugfix] EMA in distillation pipeline ( #1440 )
2026-06-06 17:38:03 -07:00
William Lin
041e5e9029
[bugfix]: unblock PyPI publish (flash-attn-cute direct dep) ( #1436 )
2026-06-05 10:07:12 -07:00
Kaiqin Kong and mergify[bot]
efcc245c2e
[feat] VLM as judge for WM ( #1429 )
...
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
2026-06-05 04:25:54 +00:00
alexzms and mergify[bot]
922e7e0813
[docs] LTX-2.3 distilled i2v example with compile + timing breakdown ( #1430 )
...
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
2026-06-05 01:26:50 +00:00
William Lin
c62a8514b0
[chore]: release v0.2.0 ( #1432 )
2026-06-04 14:22:49 -07:00
William Lin
3eb8081801
[chore]: unpin runtime deps in pyproject.toml ( #1431 )
2026-06-04 13:46:49 -07:00
Raghav K
3505d09564
[bugfix] tests: include ltx2_3_base in expected LTX2 preset set ( #1427 ) ( #1428 )
2026-06-04 12:17:18 -07:00
Shao Duan and SolitaryThinker
570607945c
[feat] dreamverse: sequence parallelism for serving ( #1424 )
...
Co-authored-by: SolitaryThinker <wlsaidhi@gmail.com >
2026-06-01 23:13:49 -07:00
Kaiqin Kong and SolitaryThinker
d3a821cdcf
[feat] LoRA controls and integration for Dreamverse ( #1420 )
...
Co-authored-by: SolitaryThinker <wlsaidhi@gmail.com >
2026-06-01 18:54:11 -07:00
Kaiqin Kong
3f24578139
[bugfix] LTX2: honor video_position_offset_sec in the DiT ( #1422 )
2026-06-01 16:59:15 -07:00
Kevin Lin
89fcf08378
[bugfix] Fix STFT dtype mismatch ( #1419 )
2026-05-31 20:56:07 -07:00
c2930b2aa1
[ci] Add additional Dreamverse UI tests ( #1417 )
...
Co-authored-by: SolitaryThinker <wlsaidhi@gmail.com >
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
2026-05-31 19:53:29 -07:00
KUAN-HAO HUANG and SolitaryThinker
019239690b
[perf] Add Adaptive Guidance (CFG gating) for stale-uncond reuse ( #1372 )
...
Co-authored-by: SolitaryThinker <wlsaidhi@gmail.com >
2026-05-30 13:58:55 -07:00
alexzms
d6119c1f82
[bugfix]: dreamverse modal bypasses ENTRYPOINT — set ffmpeg env + key check ( #1413 )
2026-05-29 16:50:01 -07:00
alexzms
84214c80bb
[feat] LTX-2.3 audio: BWE vocoder path ( #1398 )
2026-05-29 16:43:26 -07:00
alexzms and mergify[bot]
c2d7143c72
[feat] LTX-2.3 transformer support (config-gated extension of LTX-2) ( #1397 )
...
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
2026-05-29 16:42:37 -07:00
Kaiqin Kong and SolitaryThinker
afdb6fbfa5
[feat] Add MatrixGame3.0 ( #1201 )
...
Co-authored-by: SolitaryThinker <wlsaidhi@gmail.com >
2026-05-27 21:07:01 +00:00
alexzms
ba4c02d883
[docs]: highlight Dreamverse deployment paths + add Server B200 (SSH) guide ( #1409 )
2026-05-27 09:30:58 -07:00
Junda Su
2c137931f3
[bugfix] Fix Dreamverse Modal compile warmup latency ( #1394 )
2026-05-26 17:58:38 -07:00
Shao Duan
36682797a0
[feat] eval: input ergonomics + Evaluator features + bug fixes ( #1392 )
2026-05-26 13:59:45 -07:00
William Lin
0ef1357a77
[docs]: surface activation-trace utility in add-model skills ( #1399 )
2026-05-26 13:45:12 -07:00
William Lin
a75d19786a
[docs]: Wire activation trace into mkdocs nav + perf/troubleshooting ( #1304 )
2026-05-26 13:14:36 -07:00
alexzms
be548a78ea
[feat] VSA-256 fastpath on Blackwell via FA4 CuTe block-sparse attention ( #1354 )
2026-05-26 12:58:29 -07:00
alexzms
6a610e2bc9
[ci] add per-method single-step training tests for fastvideo.train ( #1343 )
2026-05-25 17:09:54 -07:00
Shao Duan and abaghyangor
321d5112b4
[refactor] eval: consolidate FVD into common.fvd, remove benchmarks/fvd ( #1380 )
...
Co-authored-by: abaghyangor <abaghyangor@gmail.com >
2026-05-24 12:09:47 -07:00
William Lin
ba75ad82db
[refactor]: shared attention infra additions for QAT-compat (Attn-QAT 5/12) ( #1383 )
2026-05-23 16:19:24 -07:00
Junda Su
58caa5109f
[ci] Add DreamVerse app CI tests ( #1386 )
2026-05-23 14:28:26 -07:00
2f3ca8aaad
[perf]: register FA2/FA3 default flash_attn_func as a torch.library custom op ( #1373 )
...
Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com >
Co-authored-by: SolitaryThinker <wlsaidhi@gmail.com >
2026-05-23 00:39:06 -07:00
SolitaryThinker