GitLab

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>

Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
(cherry picked from commit 8ebf271b)

Signed-off-by: Nick Hill <nickhill123@gmail.com>

Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>

Signed-off-by: Alex Sun <alex.s@amd.com>

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

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

Signed-off-by: walterbm <walter.beller.morales@gmail.com>

Signed-off-by: Karan Bansal <karanb192@gmail.com>

区分pcie和hglink custom allreduce的使用
vllm：export VLLM_CUSTOM_CACHE=1
dtk：export HIP_KERNEL_EVENT_SYSTENFENCE=1

set VLLM_USE_FUSED_RMS_ROPE=1
add SUPPORT_MOE_MARLIN_W16A16 to use moe marlin on bw
support fa kvcache fp8 (todo: add VLLM_USE_QUERY_QUANT to not use q quant)
update moe_align_block_size

fix _forward_encoder_attention
remove medusa
set VLLM_PCIE_USE_CUSTOM_ALLREDUCE=1

Signed-off-by: Tomer Natan <tbarnatan@computelab-frontend-8.nvidia.com>
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Tomer Natan <tbarnatan@computelab-frontend-8.nvidia.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Tomer Natan <tbarnatan@ipp1-1429.ipp1a1.colossus.nvidia.com>

Signed-off-by: Aleksandr Malyshev <maleksan@amd.com>
Co-authored-by: Aleksandr Malyshev <maleksan@amd.com>

[ROCm][Perf] Enable shuffle kv cache layout and assembly paged attention kernel for `AiterFlashAttentionBackend` (#29887)
Signed-off-by: ganyi <ygan@amd.com>

Signed-off-by: LopezCastroRoberto <roberto.lopez.castro@udc.es>
Signed-off-by: Roberto L. Castro <38211239+LopezCastroRoberto@users.noreply.github.com>
Signed-off-by: LopezCastroRoberto <rocastro@redhat.com>

Signed-off-by: Fadi Arafeh <fadi.arafeh@arm.com>

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