GitLab

fix _forward_encoder_attention
remove medusa
set VLLM_PCIE_USE_CUSTOM_ALLREDUCE=1

update weights_not_loaded and flash_mla_with_kvcache
update paged_mqa_logits

Signed-off-by: Yifan Qiao <yifanqiao@berkeley.edu>
(cherry picked from commit 11a89cf9)

(cherry picked from commit 74a1ac38)

修复CompressedTensorsLinearMethod中的w4a16的冲突问题
feat(moe): add Marlin W16A16 fused MoE behind VLLM_USE_MARLIN_W16A16_MOE
replace the fp8_mqa_logits and fp8_paged_mqa_logits interfaces in deepgemm with mqa_logits and paged_mqa_logits from lightop

Signed-off-by: drslark <slarksblood@qq.com>

Signed-off-by: LopezCastroRoberto <robertol.c510@gmail.com>
Signed-off-by: Roberto L. Castro <38211239+LopezCastroRoberto@users.noreply.github.com>
Co-authored-by: youkaichao <youkaichao@gmail.com>

Signed-off-by: Jan van Lunteren <jvl@zurich.ibm.com>
Signed-off-by: jvlunteren <161835099+jvlunteren@users.noreply.github.com>
Co-authored-by: Thomas Parnell <tom.parnell@gmail.com>
Co-authored-by: Thomas Parnell <tpa@zurich.ibm.com>

Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>

Signed-off-by: Ming Yang <minos.future@gmail.com>

Signed-off-by: Po-Han Huang <pohanh@nvidia.com>

Signed-off-by: Aditya Tewari <aditya.tewari@arm.com>

[Attention] Make seq_lens_cpu optional in CommonAttentionMetadata to enable true async spec-decode (#29624)
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Signed-off-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
Co-authored-by: Benjamin Chislett <chislett.ben@gmail.com>

Signed-off-by: FENP <yuanyongjie.yyj@antgroup.com>

Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Signed-off-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
Co-authored-by: Benjamin Chislett <chislett.ben@gmail.com>

Signed-off-by: Siyuan Fu <siyuanf@nvidia.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: Jingchun Gao <gaojingchun1@huawei.com>
Signed-off-by: Jingchun Gao <63247409+gjc0824@users.noreply.github.com>
Co-authored-by: Jingchun Gao <gaojingchun1@huawei.com>

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

This reverts commit 3b121add.

add VLLM_USE_OPT_RESHAPE_AND_CACHE、VLLM_USE_FUSE_SILU_AND_MUL and VLLM_USE_TOPK_RENORM for qwen3-30b

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

Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Signed-off-by: baonudesifeizhai <baonudesifeizhai@gmail.com>
Co-authored-by: baonudesifeizhai <baonudesifeizhai@gmail.com>

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

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

Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>

Signed-off-by: augusto.yjh <augusto.yjh@antgroup.com>

Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>

Signed-off-by: Andrii Skliar <askliar@askliar-mlt.client.nvidia.com>
Co-authored-by: Andrii Skliar <askliar@askliar-mlt.client.nvidia.com>

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

[Attention][Async] Eliminate `seq_lens_cpu` in FlashAttention metadata building with DCP > 1 (#29449)
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>