Commit Graph
883 Commits
Author SHA1 Message Date
k1kong 1e2f2bfbca fix fir transformer 5.10.2 2026-07-07 15:00:49 -07:00
H1yori233 5e90f421d5 fix 2026-07-07 15:00:49 -07:00
H1yori233 546ad1fb32 deterministic pipeline parity 2026-07-07 15:00:49 -07:00
H1yori233 9e261fef21 fix 2026-07-07 15:00:49 -07:00
H1yori233 ea4b2d3195 some fix 2026-07-07 15:00:49 -07:00
H1yori233 c7767910d2 precommit 2026-07-07 15:00:49 -07:00
H1yori233 cc61fc2714 lower SSIM resolution 2026-07-07 15:00:49 -07:00
H1yori233 a0749e98fd cleanup and local test 2026-07-07 15:00:49 -07:00
Shreejith SG 2d7e262b13 chore: remove unused reference image 2026-07-07 15:00:49 -07:00
Shreejith SG 65de01f1f1 Baseline: Deterministic priors, debug logs, SSIM 0.715 2026-07-07 15:00:49 -07:00
Shreejith SG e20deeb5eb fix(glm-image): resolve SSIM issues by fixing T5 glyph shapes and KV cache dimensions 2026-07-07 15:00:49 -07:00
Shreejith SG 51b9761334 Revert fix 2026-07-07 15:00:49 -07:00
Shreejith SG e99d2d9f16 Numerical alignment fix 2026-07-07 15:00:49 -07:00
Shreejith SG 8a9ec8621e enable sampling for quality 2026-07-07 15:00:49 -07:00
Shreejith SG 53440d4562 CI fix - Upgrade transformers and accelerate versions 2026-07-07 15:00:49 -07:00
Shreejith SG 3d82e5e24c Fix pre-commit errors and SSIM test ImportError 2026-07-07 15:00:49 -07:00
Shreejith SG cc2c419c4b Fix mypy error: add __init__ to GlmImageDecodingStage 2026-07-07 15:00:49 -07:00
Shreejith SG 81fb8f2c10 Add GLM-Image SSIM test and fix deterministic latent generation 2026-07-07 15:00:49 -07:00
Shreejith SG 0d80a668d2 Add L40S reference image for GLM-Image 2026-07-07 15:00:49 -07:00
Shreejith SG 9dec070d4c Fix GLM-Image seed handling and add SSIM test 2026-07-07 15:00:49 -07:00
ShreejithSG 326287dffa WIP: add GLM-Image SSIM test and diffusers reference generator 2026-07-07 15:00:49 -07:00
ShreejithSG 5c68193009 Refactor GLM-Image decoding stage to inherit from our DecodingStage 2026-07-07 15:00:49 -07:00
ShreejithSG 19ef9fa56f Refactor attn mask handling to use forward context 2026-07-07 15:00:49 -07:00
ShreejithSG 7833575da8 Fix PR comments: simplify example script and properly handle attention_mask through forward context
- Clean up basic_glm_image.py to match other example scripts (remove unnecessary comments, follow LTX2 pattern)
- Fix attention_mask handling in LocalAttention to use set_forward_context properly instead of creating SDPAMetadata inline
- SDPAMetadata import remains at top of file (no local import)
2026-07-07 15:00:49 -07:00
ShreejithSG 9ea387e872 Address more PR review comments 2026-07-07 15:00:49 -07:00
ShreejithSG 615da36296 Fix precommit error 2026-07-07 15:00:49 -07:00
ShreejithSG c54e0737d0 Address PR comments: GLM-Image Port to FastVideo- Replaced diffusers FeedForward with FastVideo MLP in DiT.- Moved SDPAMetadata import to top of attention layer for cleaner code.- Removed unnecessary __call__ override from pipeline to use standard composition.- Consolidated CFG into a single batched pass with concatenated embeddings for performance.- Fixed attention mask compatibility issues with optimized FLASH_ATTN backend.- Robustly patched flash_attn unpad utility for variable version return values. 2026-07-07 15:00:48 -07:00
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
KaredandSolitaryThinker e2f4d1a7b5 [feat]: add SwanLab tracker (#1461)
Co-authored-by: SolitaryThinker <wlsaidhi@gmail.com>
2026-07-07 08:35:38 +00:00
Kaiqin KongandSolitaryThinker 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 LeeandSolitaryThinker 1ee11e08dc [ci]: add performance fingerprint cohorts (#1546)
Co-authored-by: SolitaryThinker <wlsaidhi@gmail.com>
2026-07-07 07:24:00 +00:00
595f0ea60e [feat] Add DreamX-World 5B Cam and AR pipelines (#1538)
Co-authored-by: Suckl <Suckl@users.noreply.github.com>
Co-authored-by: SolitaryThinker <wlsaidhi@gmail.com>
2026-07-07 06:16:18 +00:00
William Lin d921832cd2 [misc]: reserve CPU/memory for timing-sensitive Modal CI lanes (#1566) 2026-07-06 22:13:53 -07:00
William Lin 629697629a [bugfix]: free CUDA memory between train-framework model tests (LongCat OOM on L40S) (#1565) 2026-07-06 21:27:30 -07:00
William Lin a25313beec [ci]: wire fastvideo/tests/ops/ into the unit-test lane (#1559) 2026-07-06 12:07:26 -07:00
William Lin dbde64385b [bugfix]: bump FA4 pin to the CuTe DSL 4.6 compatible rev (#1564) 2026-07-06 12:06:59 -07:00
William Lin 9d909f5f04 [test]: remove dead and duplicate tests (-489 lines) (#1556) 2026-07-05 15:53:40 -07:00
William Lin 76b0550c15 [ci]: run pre-commit on fork PRs without manual approval (#1555) 2026-07-05 14:18:16 -07:00
William Lin 384c1e9493 [misc]: update reseed-performance-baseline skill for the hf_store move (#1545 follow-up) (#1553) 2026-07-05 14:16:55 -07:00
William Lin b1dbcc93f6 [misc]: reformat fastvideo/performance to the repo yapf config (#1554) 2026-07-05 14:16:20 -07:00
William Lin b93833772e [ci]: guard against test directories no CI lane collects (#1552) 2026-07-05 14:07:38 -07:00
Mac Lee 30b523edd6 [ci] Normalize performance stage component metrics (#1475) (#1550) 2026-07-05 14:05:26 -07:00
Mac LeeandSolitaryThinker 6aab7f3832 [ci] cover Hunyuan 1.5 chat-list text preprocessing (#1518)
Co-authored-by: SolitaryThinker <wlsaidhi@gmail.com>
2026-07-05 12:05:25 -07:00
Mac Lee 9cd53fe5f8 [ci] Add metric-specific performance thresholds (#1545) 2026-07-05 12:04:33 -07:00
Mac Lee 6a32cf3a5e [ci]: expose LoRA extraction slash command (#1542) 2026-07-05 06:45:31 -07:00
William Lin 98be9b3da2 [bugfix]: address the three remaining #1447 review findings (#1549) 2026-07-05 06:43:27 -07:00
Mac Lee c53e85b767 [ci] Add v2 performance benchmark config identity fields (#1544) 2026-07-05 06:18:15 -07:00
William Lin 40a8bd2d3b [bugfix]: skip ThunderKittens kernels on aarch64 and document the kernel build matrix (#1548) 2026-07-05 06:13:11 -07:00
Mac LeeandSolitaryThinker 31aa115611 [bugfix]: preserve FSDP hooks for RMSNorm qk norms (#1513)
Co-authored-by: SolitaryThinker <wlsaidhi@gmail.com>
2026-07-05 04:15:49 +00:00
zainnhandSolitaryThinker 98ac10a528 [infra] Auto-rebuild CUDA images when docker/Dockerfile changes on main (#1526)
Co-authored-by: SolitaryThinker <wlsaidhi@gmail.com>
2026-07-04 16:25:46 -07:00