[ROCm][Bugfix] Fix Mamba batched decode producing incorrect output (v…

…llm-project#32099)

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

[Bugfix] Fix tool_choice="none" being ignored by GPT-OSS/harmony mode…

…ls (vllm-project#30867)

Signed-off-by: yujiepu <pyjapple@gmail.com>
Signed-off-by: PlatinumGod <pyjapple@gmail.com>
Co-authored-by: Chauncey <chaunceyjiang@gmail.com>

Check for truthy `rope_parameters` not the existence of it (vllm-proj…

…ect#30983)

Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
(cherry picked from commit 19c5833)

[v1] Add PrefixLM support to TritonAttention backend (vllm-project#30386

)

(cherry picked from commit 74a1ac3)

[XPU] fix broken fp8 online quantization for XPU platform (vllm-proje…

…ct#30831)

Signed-off-by: Yan Ma <yan.ma@intel.com>
(cherry picked from commit 4f735ba)

[ROCm] [Bugfix] Fix torch sdpa hallucination (vllm-project#30789)

Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
(cherry picked from commit 2410132)

fake rc release to fix nightly wheels

[Core] Rename PassConfig flags as per RFC vllm-project#27995 (vllm-pr…

…oject#29646)

Signed-off-by: arpitkh101 <arpit5khandelwal@gmail.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
(cherry picked from commit d7284a2)

[BugFix] Fix false assertion with spec-decode=[2,4,..] and TP>2 (vllm…

…-project#29036)

Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
(cherry picked from commit 8f4f77a)

[BugFix] Fix PP/async scheduling with pooling models (vllm-project#28899

)

Signed-off-by: Nick Hill <nhill@redhat.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>