4 people ff1ce11348 [diffusion] model: support VDN-H3 with a hybrid_window_attn_h3 backend (#37903) ...

Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
Co-authored-by: Haocheng Xi <xihc@berkeley.edu>
Co-authored-by: Mick <mickjagger19@icloud.com>

2026-09-12 11:36:32 +08:00

..

advanced_features

[AMD] Allow aiter attention backend for Gemma-4 (#38758)

2026-09-11 18:48:26 -07:00

basic_usage

[Docs] Clarify OpenAI chat template defaults (#32172)

2026-09-05 05:22:05 +08:00

developer_guide

[Deps] Retire the CUDA 12 lane (#38404)

2026-09-10 16:58:09 -07:00

get-started

[Deps] Retire the CUDA 12 lane (#38404)

2026-09-10 16:58:09 -07:00

hardware-platforms

[NPU] Bump memfabric and sgl-kernel-npu versions in docs and pyproject_npu.toml (#38437)

2026-09-09 19:53:49 +08:00

references

[NVIDIA] Support flashinfer Mega Moe (#31470)

2026-09-10 00:22:47 -07:00

sglang-diffusion

[diffusion] model: support VDN-H3 with a hybrid_window_attn_h3 backend (#37903)

2026-09-12 11:36:32 +08:00

supported-models

Add Ling-3.0-flash-VL cookbook (#38434)

2026-09-08 23:00:24 +08:00

supported-models.mdx

[Docs] Rename docs_new/ to docs/ (#32123)

2026-08-03 16:51:00 -07:00