GitLab

  新增环境变量 VLLM_USE_LIGHTOP_MOE_SUM_MUL_ADD 用于控制
  fused sum+mul+add 开关。
  在 DeepseekV2MoE 中增加 fused 路径，预计算 shared_output，并下传 iqis 与 routed_scaling_factor。
  扩展 FusedMoE/SharedFusedMoE 及相关 custom op 接口，统一透传 i_q/i_s/shared_output/routed_scaling_factor。
  同步适配 Triton、Marlin W16A16、SlimQuant W4A8、CompressedTensors W8A8 等实现，支持在内核侧完成 sum+mul+add。

Signed-off-by: Robert Shaw <rshaw@neuralmagic.com>

Signed-off-by: zhewenli <zhewen@inferact.ai>
Co-authored-by: zhewenli <zhewen@inferact.ai>

Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
(cherry picked from commit 07978117)

Signed-off-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>
(cherry picked from commit 31aedfe7)

Signed-off-by: Robert Shaw <robshaw@redhat.com>
Signed-off-by: Amir Klein <203507526+amirkl94@users.noreply.github.com>
Co-authored-by: Robert Shaw <robshaw@redhat.com>
Co-authored-by: amirkl94 <203507526+amirkl94@users.noreply.github.com>

Signed-off-by: Pengchao Wang <wpc@fb.com>

Signed-off-by: dafrimi <dafrimi@nvidia.com>
Co-authored-by: root <root@gpu-51.slurm-workers-slurm.slurm.svc.cluster.local>

Signed-off-by: LopezCastroRoberto <rocastro@redhat.com>

Signed-off-by: jon <joninco@bullpoint.org>

Signed-off-by: yewentao256 <zhyanwentao@126.com>

Signed-off-by: mgoin <mgoin64@gmail.com>

Signed-off-by: Xin Yang <xyangx@amazon.com>

[torch.compile] Compile `CustomOp.forward_native` for `SiluAndMul` and `QuantFP8` to avoid raw torch ops inside opaque custom ops (#32806)
Signed-off-by: Luka Govedič <lgovedic@redhat.com>
Signed-off-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>

Signed-off-by: Bill Nell <bnell@redhat.com>

Signed-off-by: Xin Yang <xyangx@amazon.com>

Signed-off-by: Eldar Kurtic <8884008+eldarkurtic@users.noreply.github.com>
Signed-off-by: eldarkurtic <8884008+eldarkurtic@users.noreply.github.com>

Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>

Signed-off-by: elvischenv <219235043+elvischenv@users.noreply.github.com>

Signed-off-by: Robert Shaw <robshaw@redhat.com>
Co-authored-by: Robert Shaw <robshaw@redhat.com>