GitLab

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: Matthew Wong <Matthew.Wong2@amd.com>

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

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

[ROCm][Bugfix] Fix accuracy issue on fmoe when `VLLM_ROCM_USE_AITER_FUSION_SHARED_EXPERTS` enabled (#31523)
Signed-off-by: ganyi <ygan@amd.com>

Signed-off-by: c0de128 <kevin.mckay@outlook.com>
Co-authored-by: Claude Sonnet 4.5 <noreply@anthropic.com>

Signed-off-by: Andreas Karatzas <akaratza@amd.com>

Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>

[Platform] Refactor Platform attention backend selection to avoid breakpoint for OOT platform (#30212)
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Signed-off-by: Isotr0py <2037008807@qq.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>

[CustomOp][MM] Extract MMEncoderAttention as CustomOp and replace the backend of QwenVisionAttention with it. (#30125)
Signed-off-by: shen-shanshan <467638484@qq.com>
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: tjtanaa <tunjian.tan@embeddedllm.com>

Signed-off-by: Andreas Karatzas <akaratza@amd.com>

Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>

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

Signed-off-by: QiuChunshuo <qiuchunshuo@huawei.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>

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

Signed-off-by: Micah Williamson <micah.williamson@amd.com>

Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>

Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>

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

Signed-off-by: ganyi <ygan@amd.com>

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

Signed-off-by: sstamenk <strahinja.stamenkovic@amd.com>

Signed-off-by: Huamin Li <3ericli@gmail.com>

Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>

[ROCM] Fix ROCm warnings, environment flag access, and GEMM kernel naming for consistency in `_aiter_ops.py` (#28464)
Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>

Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>

Signed-off-by: Andreas Karatzas <akaratza@amd.com>
Signed-off-by: Andreas Karatzas <Andreas.Karatzas@amd.com>

Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Signed-off-by: Matthew Bonanni <mbonanni001@gmail.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>

[RFC][ROCm][AITER] Keep all AITER kernels in `_aiter_ops` class like `_custom_ops` and `_ipex_ops` (#24490)
Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>

Signed-off-by: JartX <sagformas@epdcenter.es>

Signed-off-by: ganyi <ygan@amd.com>
Co-authored-by: wuhuikx <hattie.wu@amd.com>

Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>