Commit Graph
100 Commits
Author SHA1 Message Date
Mick 4682ded472 vlm: parallelize multimodal preprocessing with customized worker num (#31438) 2026-07-21 08:44:58 +08:00
Mick 2eed35d738 perf: avoid temporary VLM encoder gather padding (#31301) 2026-07-20 12:54:29 +08:00
Mick 6a25dd7b5f fix: warm up Kimi VLM vision encoder at startup (#31298) 2026-07-20 08:50:57 +08:00
Mick d4801be447 fix: fix vlm cuda graph shape stability (#30868) 2026-07-19 22:35:51 +08:00
Mick 573c075fef CI: synchronize prefill graph test fixtures (#31665) 2026-07-18 18:48:05 +08:00
Mick 6c6175fabd perf: avoid excessive prefill CUDA graph padding (#31487) 2026-07-18 16:25:30 +08:00
Mick 42a058c760 optimize: avoid fla l2-norm recompilation by token count (#31558) 2026-07-18 07:58:36 +08:00
Mick 85ac56c823 docs: simplify diffusion new model guide (#30109) 2026-07-17 19:39:38 +08:00
Mick 681c223570 refactor: wrap split backends once on full-attention backends (#31439) 2026-07-17 19:15:04 +08:00
Mick 24a8944e15 fix: enable Kimi multimodal breakable prefill cuda graph replay (#31391) 2026-07-17 19:13:54 +08:00
Mick 7d0fd5101d optimization: shard kimi dp image feature transport and misc optimizations (#31227) 2026-07-16 20:31:42 +08:00
Mick d9003dd452 fix: skip unsafe automatic prefill graph capture (#31204) 2026-07-16 09:27:38 +08:00
Mick 947a14d617 feat: unify multimodal feature transport (#30904) 2026-07-15 17:42:38 +08:00
Mick 43124cdd90 fix: fix image benchmark backend parity (#30867) 2026-07-15 10:11:22 +08:00
Mick 04af94d150 fix: avoid tilelang cuda runtime pollution (#30870) 2026-07-14 22:30:27 +08:00
Mick 43241b7f3f [diffusion] model: support fal Ideogram V4 Fast and Instant (#31177) 2026-07-14 19:51:35 +08:00
Mick 23b2c6f1ce docs: fix diffusion cookbook overview cards (#31101) 2026-07-14 10:40:42 +08:00
Mick 33f83011e0 fix: fix Kimi-VL encoder parallelism (#30869) 2026-07-14 08:44:06 +08:00
Mick 7da30f4e55 feat: enable piecewise prefill graph for Kimi K2.5/K2.7 (#30889) 2026-07-13 08:37:30 +08:00
Mick f1c247edf9 profile: add vlm prefill profiler ranges (#30871) 2026-07-12 14:07:10 +08:00
Mick bce3fc987d perf: reuse MoonViT FA3 max-seqlen metadata (#30878) 2026-07-12 14:05:21 +08:00
Mick a358abd651 chore: update vlm moe config and tune scripts (#30866) 2026-07-12 08:35:59 +08:00
Mick af66370d81 bench: support random image resolutions (#30879) 2026-07-12 08:28:56 +08:00
Mick 649ce5dd3d model: support Pi0.5 (#30633) 2026-07-11 07:50:58 +08:00
Mick 559854fe6a [diffusion] docs: sync cookbook and log hygiene (#30791) 2026-07-10 22:55:14 +08:00
Mick 7090a49198 update codeowners (#30788) 2026-07-10 22:35:34 +08:00
Mick 4a8e1b07a2 [diffusion] refactor: reorganize runtime utility and server_args modules (#30447) 2026-07-10 15:53:00 +08:00
Mick 5ce5e1ee3e [Diffusion] Revert CPU AMX optimizations (#30716) 2026-07-10 09:09:38 +08:00
Mick 6c1fb8a937 [diffusion] fix: fix ragged-caption dynamic-batching accuracy bug in ernie-Image (#30241) 2026-07-07 08:41:51 +08:00
Mick 5f98f62a8a [diffusion] perf: tp-shard every text/image encoder across the full DiT replica (any parallelism) (#30086) 2026-07-06 14:48:07 +08:00
Mick a37bc2456d [diffusion] refactor: consolidate diffusion weight load planning (#30118) 2026-07-05 11:59:50 +08:00
Mick 763c6bf372 [diffusion] perf: add unified SP shard helpers and zero-copy tail-pad attention (#30107) 2026-07-04 23:57:39 +08:00
Mick 36fc0093d6 [diffusion] fix: shut down diffusion workers on serve exit (#30110) 2026-07-04 20:42:39 +08:00
Mick 03962d4238 [diffusion] feat: enable compile warmup for vae decode (#29306) 2026-07-04 15:25:26 +08:00
Mick 5af1f949ca [diffusion] CI: prefer official diffusion consistency GT (#29831) 2026-07-04 10:09:33 +08:00
Mick 486bcb48e7 [diffusion] CI: fix AMD diffusion CI import (#30039) 2026-07-03 22:26:08 +08:00
Mick 42acfd1550 [diffusion] feat: performance_mode=speed enables torch.compile by default (#30016) 2026-07-03 19:12:17 +08:00
Mick 3c1adddff9 [diffusion] refactor: refactor cuda attention backend resolver (#29852) 2026-07-02 21:34:54 +08:00
Mick 119b76567d [diffusion] feat: add --offload-during-compile to fit max-autotune on tight-memory GPUs (#29862) 2026-07-02 19:39:19 +08:00
Mick 03b9278da0 [diffusion] CI: tighten multimodal-gen consistency thresholds (#29824) 2026-07-02 01:32:51 +08:00
Mick 79f334b1aa [diffusion] CI: add 5090 job (#29791) 2026-07-01 19:09:43 +08:00
Mick 2068ae7eec [diffusion] chore: document VAE decode parallel group axes (#29364) 2026-06-30 12:14:55 +08:00
Mick 25b6051c70 [diffusion] warmup: default to model sampling resolution (declare Z-Image default) (#29519) 2026-06-30 10:32:11 +08:00
Mick b0be644133 [diffusion] feat: keep image-model auxiliary components resident under auto memory policy (#29649) 2026-06-30 01:25:37 +08:00
Mick 4cb6d81bda [diffusion] CI: make consistency GT probe robust to transient CDN failures (#29545) 2026-06-28 17:13:53 +08:00
Mick 97ddc66209 [diffusion] nightly: track SGLang-Diffusion only (#29434) 2026-06-28 14:23:17 +08:00
Mick 643e1cc779 fix: fix prefill-aware SWA floor tracking (#29520) 2026-06-28 14:18:28 +08:00
Mick 4a76699dfc [diffusion] fix: fix --warmup silently downgrading server-based warmup to request mode (#29514) 2026-06-28 11:46:07 +08:00
Mick cfd911ad6e docs: refine diffusion cookbook overview (#29507) 2026-06-28 00:10:21 +08:00
Mick 3306233961 [diffusion] optimize: optimize LTX2.3 CFG path (#28624) 2026-06-27 19:23:14 +08:00
Mick 91f9e7372d [diffusion] CI: refactor CI (#28762) 2026-06-27 19:22:27 +08:00
Mick 890b38c211 [diffusion] doc: fix diffusion docs and cookbook drift (#29302) 2026-06-25 21:13:00 +08:00
Mick 4a4f063b79 [diffusion] fix: paint multiview vae must follow unit dtype (#29041) 2026-06-24 23:54:01 +08:00
Mick 09b808ab7e [diffusion] fix: fix Qwen-Image-Layered latent shape (#28832) 2026-06-24 20:57:54 +08:00
Mick 219742c394 [diffusion] optimize: optimize realtime causal attention fastpath (#28760) 2026-06-23 15:15:30 +08:00
Mick bbe8b7dd8a [diffusion] CI: restore Hunyuan3D-2 image-to-3D (#28781) 2026-06-22 23:36:18 +08:00
Mick 4923bb93ae [diffusion] CI: fix turbo_wan/flux invisible CI cases (#28913) 2026-06-22 21:21:16 +08:00
Mick ead39d38fc [diffusion] refactor: refactor causal KV local head cache updates (#28888) 2026-06-22 21:00:38 +08:00
Mick 2b2cd21783 [diffusion] fix: reject cache-dit with fsdp (#28834) 2026-06-22 10:47:40 +08:00
Mick 320b231ea6 [diffusion] chore: bound DiffGenerator local cleanup (#28833) 2026-06-21 22:23:49 +08:00
Mick a7f31a6e1b [diffusion] fix: fix SANA-WM CFG-parallel tensor devices (#28835) 2026-06-21 22:01:00 +08:00
Mick a51d56d948 CI: Pin flash-attn-4 for diffusion CI consistency (#28838) 2026-06-21 21:13:41 +08:00
Mick c65f4ea692 [diffusion] fix: validate openai sampling dimensions (#28791) 2026-06-21 09:44:38 +08:00
Mick 6a16573a7f [diffusion] fix: fix Qwen-Image-Layered string image paths (#28790) 2026-06-21 09:43:56 +08:00
Mick 1109acc24b [diffusion] optimize: shard hunyuan text tokens under sp (#28319) 2026-06-20 18:21:38 +08:00
Mick a38eba0f1a [diffusion] CI: remove flaky layerwise offload diffusion case (#28778) 2026-06-20 17:27:27 +08:00
Mick af2ec2a0dd [diffusion] perf: merge LTX-2 stage-1 distilled LoRA into the base in original mode (#28594) 2026-06-19 15:41:47 +08:00
Mick 547a017a77 [diffusion] CI: run nightly image comparisons on 2 GPUs (#28593) 2026-06-19 13:43:02 +08:00
Mick 3b61dc32c9 [diffusion] fix: fix fp8 fused tp scale loading (#28546) 2026-06-18 14:38:38 +08:00
Mick 05b3fd0f44 [diffusion] chore: remove ltx2 snapshot mode (#28533) 2026-06-18 10:20:21 +08:00
Mick 735a256f98 [diffusion] feat: use LocalAttention for mistral3 encoder (#28176) 2026-06-17 21:18:41 +08:00
Mick 0f5e14e1d9 [diffusion] fix: use Megatron-style tp for native encoders and dits (#28318) 2026-06-17 13:07:44 +08:00
Mick c17190c059 update codeowners (#28478) 2026-06-17 11:16:52 +08:00
Mick a4a8a614b1 [diffusion] UX: suppress noisy diffusers torchao warning (#28317) 2026-06-16 10:32:21 +08:00
Mick 01e45762ba [diffusion] feat: use srt custom allreduce for tp groups (#28324) 2026-06-16 09:22:47 +08:00
Mick 818808d152 [diffusion] optimize: optimize causal conv3d vae padding (#28204) 2026-06-15 20:18:08 +08:00
Mick 578e936d8d [diffusion] feat: persist torch.compile inductor/triton cache across restarts (#28205) 2026-06-15 13:34:19 +08:00
Mick 3cb29f6747 [diffusion] feat: use regional torch.compile (compile_repeated_blocks) for DiT of diffusers backend (#28193) 2026-06-15 00:34:10 +08:00
Mick ec36dde580 [diffusion] feat: add --warmup-mode enum server arg (#28184) 2026-06-14 23:09:04 +08:00
Mick 582bd23f71 [diffusion] feat: enable spatial-shard vae decode across GPUs (#28071) 2026-06-14 20:19:44 +08:00
Mick 5331de0f8c [diffusion] chore: resolve model_index.json Hub-first with local-cache fallback (#28177) 2026-06-14 16:48:38 +08:00
Mick 1456eb612d [diffusion] CI: tighten perf baselines (#28123) 2026-06-14 15:50:21 +08:00
Mick 37ed10bd24 [diffusion] UX: reduce attention backend log noise (#28169) 2026-06-14 14:55:13 +08:00
Mick 31ac743484 [diffusion] chore: improve server warmup coverage (#28127) 2026-06-14 13:35:42 +08:00
Mick cb4933b22e [diffusion] optimize: enable vae parallel decode with cfg-parallel (#27875) 2026-06-13 13:52:27 +08:00
Mick 8becb37519 [diffusion] warmup: improve diffusion server warmup (#28119) 2026-06-13 13:04:10 +08:00
Mick 8038806557 [diffusion] optimize: optimize flux1 tensor parallel sharding (#27826) 2026-06-12 13:13:18 +08:00
Mick d9110d971e [diffusion] fix: fix wan ti2v sp timestep padding (#27876) 2026-06-11 22:13:25 +08:00
Mick 9e9fde1478 [diffusion] Revert "Mistral3 add tensor parallel support for diffusion text encoder " (#27892) 2026-06-11 20:33:45 +08:00
Mick e8a437ef26 [diffusion] doc: update docs architecture (#27767) 2026-06-10 14:18:10 +08:00
Mick 56f06278c6 [diffusion] refactor: refactor realtime control state and adapters (#27698) 2026-06-10 12:27:16 +08:00
Mick af55025644 [diffusion] refactor: refactor realtime and model-specific stage modules (#27697) 2026-06-10 09:39:06 +08:00
Mick f6d53d6d16 docs: update SANA-WM cookbook serve examples (#27626) 2026-06-09 11:44:31 +08:00
Mick 02be2e7189 [diffusion] support tp for ideogram4 (#27393) 2026-06-07 23:14:58 +08:00
Mick bf66b7b6da [diffusion] model: support Ideogram4 NVFP4 (#27379) 2026-06-06 11:14:28 +08:00
Mick e8668508d1 [diffusion] optimize: optimize LingBot realtime sp cache path (#27383) 2026-06-06 09:37:29 +08:00
Mick 4ef081b903 [diffusion] optimize: optimize LingBot realtime transport and camera conditioning (#27297) 2026-06-05 16:00:48 +08:00
Mick e4a01d5ee2 [diffusion] fix: fix realtime webui recording timeline (#27249) 2026-06-04 19:58:56 +08:00
Mick 9e2ad6054c [diffusion] feat: speed up lossless realtime rgb transport (#27236) 2026-06-04 16:59:23 +08:00
Mick 11605767e0 [diffusion] optimize: skip unused wanvae halo send copies (#27151) 2026-06-04 10:23:01 +08:00