QianCyrusandHongsheng Liu 8ef77be66e [Model] Avoid repeated attention and MLP work in Klein TP (#8553) ...

Signed-off-by: QianCyrus <101633534+QianCyrus@users.noreply.github.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>

2026-10-07 21:21:05 +08:00

..

anima

[Model] Add circlestone-labs/Anima (#4083)

2026-09-19 16:16:38 +00:00

auk

[Perf][AuK] Graph the encoder prefill, cache reference latents and fuse the codec activation (#8305)

2026-10-02 15:43:55 +00:00

bagel

[Bugfix][BAGEL] Keep replicated prefill and cache-update phases off the SP strategy (#8177)

2026-09-29 03:45:49 +00:00

boogu_image

[Rebase] Align vLLM-Omni with vLLM v0.31.0 (#8459)

2026-10-05 14:11:01 +08:00

cosmos3

[feature] Add HSDP pre-sharded option (#7948)

2026-10-02 09:35:09 +00:00

dmd2

[Feature] Add official LTX multimodal guidance and precision guard (#5148)

2026-07-28 10:44:25 +00:00

dreamzero

[Rebase] Rebase to vLLM 0.29.0 (#7230)

2026-09-10 12:08:28 +08:00

ernie_image

[Feature] Transfer AR-to-diffusion payloads over NIXL (#6264)

2026-09-23 18:26:53 +08:00

flux

[Chore]: refactor out unused/redundant params in diffusion pipelines (#1235)

2026-07-02 16:32:05 +02:00

flux2

[Model] Avoid repeated attention and MLP work in Klein TP (#8553)

2026-10-07 21:21:05 +08:00

glm_image

[Rebase] Rebase to vLLM 0.30.0 (#7820)

2026-09-22 15:52:01 +00:00

gr00t

[Bugfix][Model] GR00T-N1.7: honor the per-request seed for flow-matching noise (#7253)

2026-09-08 15:53:20 +00:00

helios

[Bugfix][Helios] Guard cross-attn KV cache against address reuse (#8064)

2026-09-30 16:44:51 +08:00

hidream_o1_image

[Model] Add HiDream-O1-Image support (#5194)

2026-08-21 14:15:37 +08:00

hunyuan_image3

[Diffusion][HunyuanImage3] Add request paged prefix caching (#7719)

2026-09-23 15:34:56 +00:00

hunyuan_video

[Core][Frontend] Support request-level batching for diffusion pipelines (#4079)

2026-06-29 18:09:19 +02:00

kandinsky6

Kandinsky6 (#8537)

2026-10-06 15:55:15 +08:00

lance

[Bugfix][Model][Lance] Support decoded video frames in video editing (#5128)

2026-09-12 04:23:24 +00:00

lingbot_video

[Bugfix] Fix washed-out LingBot Video outputs (#7037)

2026-10-02 03:57:50 +00:00

lingbot_world

[Model] Enable online FP8 linears for LingBot World (#7549)

2026-09-21 12:21:46 +00:00

longcat_image

[Kernel] Fuse LongCat paired Q/K RoPE (#7500)

2026-09-18 02:27:57 +08:00

longcat_video

[Model] Add LongCat-Video-Avatar-1.5 ai2v, at2v support (#4099)

2026-08-11 15:17:17 +08:00

ltx2

[Perf][Diffusion] Run MammothModa2 DiT attention through the shared attention layer (#7094)

2026-09-12 11:31:05 +08:00

magi2

feat(magi2): add fused BF16 routed MoE path (#7206)

2026-09-28 23:20:30 +08:00

mammoth_moda2

[CI/Build][ROCm] Reuse AITER cache for Mammoth attention tests (#8527)

2026-10-05 18:35:01 -07:00

minimax_h3

[Rebase] Align vLLM-Omni with vLLM v0.31.0 (#8459)

2026-10-05 14:11:01 +08:00

mistral_encoder

[Rebase] Rebase to vLLM 0.29.0 (#7230)

2026-09-10 12:08:28 +08:00

nextstep_1_1

[Bugfix] Preserve NextStep rectangular latent dimensions (#7853)

2026-09-21 08:26:14 -07:00

ovis_image

[Core][Frontend] Support request-level batching for diffusion pipelines (#4079)

2026-06-29 18:09:19 +02:00

pi0

Add π0 VLA model support (#4222)

2026-08-17 14:29:17 +08:00

pi05

[Model] Add π0.5 (Pi0.5) VLA model support (#6950)

2026-09-17 05:18:51 -07:00

qwen_image

[Core] Extend the shared multi-stage execution framework for mixed V1/MRv2 pipelines (#8184)

2026-09-29 07:40:57 -07:00

sana_video

[Rebase] Rebase to vLLM 0.29.0 (#7230)

2026-09-10 12:08:28 +08:00

sana_wm

[Model] Add SANA-WM support(Stage-1 only) (#4061)

2026-08-18 23:57:55 -06:00

sd3

[Chore]: refactor out unused/redundant params in diffusion pipelines (#1235)

2026-07-02 16:32:05 +02:00

seedvr2

SeedVR2: bounded long-video restoration (#8102)

2026-09-29 11:33:50 +00:00

sensenova_u1

[Perf][Diffusion] support Sensenova online fp8 (#7955)

2026-09-28 23:17:37 +08:00

stable_audio

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

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

t5_encoder

[Rebase] Rebase to vLLM 0.29.0 (#7230)

2026-09-10 12:08:28 +08:00

wan2_2

[BugFix][Diffusion] Scope Wan RMSNorm patch to NPU (#8047)

2026-09-23 15:08:02 +08:00

z_image

[New Model] Ming-Image (inclusionAI/Ming-Image-0.1-Design) Support (#8021)

2026-09-23 12:20:06 +00:00