GitLab

feat(v1 attention): 为 ROCm FlashAttention 接入 unified kv layout，并打通 mm_prefix、qq_bias 与 use_alibi_sqrt 透传
在 ROCm FlashAttention 后端增加 unified KV layout 选择逻辑
接入 unified varlen kernel 调用路径
在 FlashAttention metadata 中补充 mm_prefix_range 与 qq_bias 透传

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

add prepare_so_files to prepare so

Signed-off-by: ElizaWszola <ewszola@redhat.com>
Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Signed-off-by: Luka Govedič <luka.govedic@gmail.com>
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Signed-off-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
Signed-off-by: Luka Govedič <lgovedic@redhat.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Varun Sundar Rabindranath <varunsundar08@gmail.com>
Co-authored-by: Matthew Bonanni <mbonanni@redhat.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
Co-authored-by: Luka Govedič <luka.govedic@gmail.com>
Co-authored-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: Luka Govedič <lgovedic@redhat.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: xieli <xieli@stepfun.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

Signed-off-by: wangli <wangli858794774@gmail.com>

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

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

Signed-off-by: yuantao <2422264527@qq.com>
Signed-off-by: yt0428 <51468697+yt0428@users.noreply.github.com>
Co-authored-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>

Signed-off-by: Boyuan Feng <boyuan@meta.com>

[MM Encoder]: Migrate legacy ViT `MultiHeadAttention` to new `MMEncoderAttention` interface (#30684)
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>

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

[CI/Build] Make test_mha_attn.py run on correct platform only and check for flash_attn_varlen_func in layer.py (#29145)

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

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

Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Signed-off-by: Matthew Bonanni <mbonanni001@gmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>

Signed-off-by: mingyuanm <mingyuanm@nvidia.com>
Signed-off-by: Roger Wang <hey@rogerw.io>
Co-authored-by: Roger Wang <hey@rogerw.io>

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

Signed-off-by: Roger Wang <hey@rogerw.io>

Signed-off-by: jesse <szxfml@gmail.com>
Signed-off-by: Song Zhixin <szxfml@gmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>

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

set default_max_num_batched_tokens = 10240
update qwen3_moe of layernorm
off lightop of moe_fused_gate

Signed-off-by: NickLucche <nlucches@redhat.com>
Signed-off-by: Mark McLoughlin <markmc@redhat.com>
Co-authored-by: Mark McLoughlin <markmc@redhat.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>

Signed-off-by: David Ben-David <davidb@pliops.com>
Co-authored-by: David Ben-David <davidb@pliops.com>
Co-authored-by: Mark McLoughlin <markmc@redhat.com>

Signed-off-by: adabeyta <aabeyta@redhat.com>

Signed-off-by: Yan Ma <yan.ma@intel.com>
Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
Co-authored-by: Yejing Lai <yejing.lai@intel.com>
Co-authored-by: Guancheng Fu <110874468+gc-fu@users.noreply.github.com>
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>

[BUGFIX][ROCM] ViT FlashAttention on ROCm (no GFX9) and contiguous on qwen3vl ROCm TORCH_SDPA (#27190)
Signed-off-by: JartX <sagformas@epdcenter.es>
Co-authored-by: tjtanaa <tunjian.tan@embeddedllm.com>

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

Co-authored-by: Bradley D <4551889+bradleyhd@users.noreply.github.com>
Co-authored-by: Roger Wang <hey@rogerw.io>

Signed-off-by: Roger Wang <hey@rogerw.io>