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。

- Add VLLM_V1_USE_FA_UNIFIED_ATTN_2D 环境变量
- 0: Triton attention, 1: FA unified attention

新增环境变量与 MLA 融合接线（wrapper -> attention -> impl） 接入 lightop fused_rms_norm_rope_contiguous，保留回退路径

新增 VLLM_V1_USE_REDUCED_TOPK_TOPP_SAMPLER 开关并补充适用场景说明

在 V1 GPU 输入批预计算 max_top_k/has_any_no_top_k，native sampler 满足条件时走 reduced fast path，异常自动回退

新增 router_capture 工具，用于按 num_tokens/rank 过滤并落盘 MoE router logits
在 Qwen3MoeSparseMoeBlock 中接入采集调用，并在 torch.compile 场景下自动跳过
补充 VLLM_MOE_ROUTER_CAPTURE* 环境变量

  - 新增环境变量 `VLLM_V1_FAST_TOKEN_ID_COPY`（默认关闭）
  - 在 `CachedRequestState` 中缓存 int32 的 prompt token ids（numpy 数组）
  - 开启后在 `InputBatch` 中使用 `np.copyto` 拷贝 prompt/output token ids

  参考并移植 011/vllm 的关键提交逻辑
  新增 VLLM_USE_MOE_W16A16_TRITON 开关，并接入基于 lightop 的运行时能力探测与启用结果缓存。
  在权重加载后对 w13 与 w2 执行 W16A16 Marlin 预打包。
  W16A16 Marlin 启用时保留 monolithic 执行路径，并在 fused_experts_impl 中增加 packed 权重 fast-path。
  保持 Marlin 或 lightop 不可用时的回退行为不变。

set fp8_e4m3 only supported on nmz and support q&kvcache fp8
set VLLM_PCIE_USE_CUSTOM_ALLREDUCE=1

Signed-off-by: wanglinian <wanglinian@stu.pku.edu.cn>
Signed-off-by: wangln19 <96399074+wangln19@users.noreply.github.com>
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Signed-off-by: youkaichao <youkaichao@gmail.com>
Signed-off-by: Roger Wang <hey@rogerw.io>
Co-authored-by: wanglinian <wanglinian@stu.pku.edu.cn>
Co-authored-by: wangln19 <96399074+wangln19@users.noreply.github.com>
Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: youkaichao <youkaichao@gmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
(cherry picked from commit b539f988)

Signed-off-by: wanglinian <wanglinian@stu.pku.edu.cn>
Signed-off-by: wangln19 <96399074+wangln19@users.noreply.github.com>
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Signed-off-by: youkaichao <youkaichao@gmail.com>
Signed-off-by: Roger Wang <hey@rogerw.io>
Co-authored-by: wanglinian <wanglinian@stu.pku.edu.cn>
Co-authored-by: wangln19 <96399074+wangln19@users.noreply.github.com>
Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: youkaichao <youkaichao@gmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>

Signed-off-by: dolpm <34420038+dolpm@users.noreply.github.com>

Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>

Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>

Signed-off-by: dolpm <34420038+dolpm@users.noreply.github.com>

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