bjf-frz 2447740308 [Perf]perf: skip unused Cosmos3 I2V conditioning latents (#4614) ...

Signed-off-by: bjf-frz <frz123db@gmail.com>

2026-06-22 09:51:47 +00:00

..

bagel

[Perf/Fix] Reimplement Batched CFG Forward for Bagel (#4098)

2026-06-22 07:37:21 +08:00

cosmos3

[Perf]perf: skip unused Cosmos3 I2V conditioning latents (#4614)

2026-06-22 09:51:47 +00:00

dmd2

[Diffusion] Unify diffusion request identity on request_id (#3744)

2026-05-28 14:56:56 +08:00

dreamid_omni

[Feat] support HSDP for DreamID-Omni (#3138)

2026-05-06 13:09:39 +08:00

ernie_image

[Diffusion] Unify diffusion request identity on request_id (#3744)

2026-05-28 14:56:56 +08:00

flux

[AutoRound] Add offline quantized W4A16 model support (#1777)

2026-04-02 13:57:53 +08:00

flux2

Reject non-positive Flux2 Klein inference steps (#3717)

2026-05-19 11:52:41 +08:00

glm_image

[AutoRound] Support GLM-Image W4A16 quantization model (#3059)

2026-05-28 07:19:06 +00:00

gr00t

[Diffusion] add GR00T-N1.7 pipeline with OpenPI serving (#3798)

2026-06-20 11:45:26 +08:00

hunyuan_image3

[Feature] Add HunyuanImage3 DiT grouped step batching (#4041)

2026-06-15 20:36:41 +08:00

hunyuan_video

fix: Propagate Quantization Configuration to HunyuanVideo-1.5 I2V Transformer to Enable FP8 Layers (#4245)

2026-06-09 15:28:32 +08:00

ltx2

Cosmos3 transfer (#4379)

2026-06-21 09:59:18 +08:00

mistral_encoder

[Model] Add TP-aware MistralEncoder for FLUX.2-dev TP (#2465)

2026-05-13 12:33:55 -07:00

nextstep_1_1

[CI]: Add core_model and cpu markers for L1 use case. (#1709)

2026-03-10 17:39:37 +08:00

ovis_image

[Diffusion] Unify diffusion request identity on request_id (#3744)

2026-05-28 14:56:56 +08:00

qwen_image

[BugFix][Qwen-Image] align txt_seq_lens RoPE width with padded embeds (#4474)

2026-06-16 19:09:25 +08:00

stable_audio

[Model] Add HSDP support for Stable-Audio-Open (#2982)

2026-04-21 18:13:20 +08:00

t5_encoder

[Bugfix] T5 text encoder to render correct text in FLUX.1-dev (#2760)

2026-04-24 18:01:52 +08:00

wan2_2

[AutoRound] Support WAN2.2 W4A16 quantization model (#3353)

2026-05-21 17:54:41 +08:00

z_image

[CI]: Add core_model and cpu markers for L1 use case. (#1709)

2026-03-10 17:39:37 +08:00