Yuan Luo b9af8d2eb9 [VLM] Support apply qk norm in multi cuda streams (#15720) ...

Co-authored-by: luoyuan.luo <luoyuan.luo@antgroup.com>

2025-12-25 14:35:07 +08:00

..

sglang

[VLM] Support apply qk norm in multi cuda streams (#15720)

2025-12-25 14:35:07 +08:00

pyproject_cpu.toml

[diffusion] multi-platform: support diffusion on amd and fix encoder loading on MI325 (#13760)

2025-12-19 15:38:46 +08:00

pyproject_other.toml

[diffusion] multi-platform: support diffusion on amd and fix encoder loading on MI325 (#13760)

2025-12-19 15:38:46 +08:00

pyproject_xpu.toml

[diffusion] multi-platform: support diffusion on amd and fix encoder loading on MI325 (#13760)

2025-12-19 15:38:46 +08:00

pyproject.toml

chore: bump sgl-kernel version to 0.3.20 (#15590)

2025-12-22 12:32:34 -08:00