nodes/hao-ai-lab-FastVideo
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
913 Commits 338 Branches 8 Tags
7ae57e6fbd5a46d2b653cf26a02491e6af277bcd
Commit Graph
913 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
SolitaryThinker 7ae57e6fbd [feat] cosmos3: native video pipeline + framework denoise parity 2026-07-20 12:19:45 -07:00
SolitaryThinker 8931f1b5d7 [feat] cosmos3: native MoT sequence-packing (video) + framework parity 2026-07-20 12:19:17 -07:00
SolitaryThinker 42eb451b50 [misc] cosmos3 PORT_STATUS: strict-load done; only pipeline remains 2026-07-20 12:19:17 -07:00
SolitaryThinker f52e88e397 [feat] cosmos3: strict-load verified (identity; needs_conversion=no) 2026-07-20 12:19:17 -07:00
SolitaryThinker 5cdbf06a23 [misc] cosmos3 PORT_STATUS: VAE component framework parity verified 2026-07-20 12:19:17 -07:00
SolitaryThinker 9e799d5bf4 [feat] cosmos3: VAE config (Wan2.2 reuse) + framework parity test 2026-07-20 12:19:17 -07:00
SolitaryThinker 468c4d505e [misc] cosmos3 PORT_STATUS: DiT framework parity verified (both rope modes) 2026-07-20 12:19:17 -07:00
SolitaryThinker 99e8c404b6 [test] cosmos3: DiT unified_3d_mrope framework parity (real checkpoint) 2026-07-20 12:19:17 -07:00
SolitaryThinker 4e6a6a3d17 [feat] cosmos3: native DiT + framework parity (Cosmos3VFMTransformer) 2026-07-20 12:19:17 -07:00
SolitaryThinker 5784e0fcb5 [misc] cosmos3 PORT_STATUS: PR1 progress (arch config, framework parity ref) 2026-07-20 12:19:17 -07:00
SolitaryThinker 576a006d06 [test] cosmos3: official framework DiT parity reference (CPU/SDPA) 2026-07-20 12:19:17 -07:00
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
Zhang PeiyuanPeiyuan ZhangPeiyuan
 		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
Raghav KMrinaal DograSolitaryThinker
 		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
MookandSolitaryThinker 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
Raghav KIshan VaishClaude Opus 4.8
 		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 SGandH1yori233 d82abc271e [feat] Add GLM-Image inference support (#1030) 
Co-authored-by: H1yori233 <k1kong@ucsd.edu>
 2026-07-12 22:42:42 -07:00
Guian FangandSolitaryThinker 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