WeiQing Chen 5d3e6dc1b4 [Bugfix][MiniMax-H3] Use Hopper-safe modulation precision (#7693) ...

Signed-off-by: david6666666 <530634352@qq.com>

2026-09-18 15:16:45 +08:00

..

mot

[Model] Add BAGEL step execution and continuous batching (#6359)

2026-09-04 01:36:11 +00:00

__init__.py

[Diffusion] Qwen image support (#82)

2025-11-28 14:22:11 +08:00

activation.py

[Bugfix][XPU] Add MoTRMSNorm.forward_xpu delegating to forward_native (#5568)

2026-09-02 23:06:17 -05:00

adalayernorm.py

[Bugfix][XPU] Add MoTRMSNorm.forward_xpu delegating to forward_native (#5568)

2026-09-02 23:06:17 -05:00

custom_op.py

[Bugfix][XPU] Add MoTRMSNorm.forward_xpu delegating to forward_native (#5568)

2026-09-02 23:06:17 -05:00

fourier.py

[Diffusion] [Model] Support AudioX (#2077)

2026-05-04 10:24:35 -04:00

fused_moe.py

[Rebase] Rebase to vllm 0.27.0 (#5976)

2026-08-11 15:23:46 +00:00

fused_qk_norm_rope.py

[Kernel][Boogu-Image] Fuse Q/K RMSNorm + interleaved RoPE via fused_qk_norm_rope (#6982)

2026-09-13 09:39:27 +08:00

fused_qk_rope.py

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

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

indexed_modulation.py

[Bugfix][MiniMax-H3] Use Hopper-safe modulation precision (#7693)

2026-09-18 15:16:45 +08:00

norm.py

[Bugfix][XPU] Add MoTRMSNorm.forward_xpu delegating to forward_native (#5568)

2026-09-02 23:06:17 -05:00

qwen_select01_modulation.py

[Diffusion] Fuse Qwen-Image-Edit select01 modulation for CUDA (#5921)

2026-09-16 19:06:28 +08:00

rope.py

[Rebase] Rebase to vLLM 0.29.0 (#7230)

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