[Bugfix] Guard mixed-dtype allreduce RMSNorm quant fusions (vllm-proj…

…ect#48330)

Signed-off-by: hcenteno <hugo.centeno@estudiantat.upc.edu>
(cherry picked from commit 5f8e73c)

[docs] Fix the docs build (vllm-project#48008)

Signed-off-by: Martin Hickey <martin.hickey@ie.ibm.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
(cherry picked from commit 6cf7b26)

[P/D][Bugfix] Fix PD async KV load lookahead handling for MTP spec de…

…code (vllm-project#46694)

Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
Co-authored-by: Nick Hill <nickhill123@gmail.com>
(cherry picked from commit ae6170f)

Fix embed scaling + CUDA graphs in Transformers modelling backend (vl…

…lm-project#48010)

Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
(cherry picked from commit 56da398)

[CPU][Bugfix] Fix flaky ShortConv prefill test on ARM (uninitialized …

…weights) (vllm-project#47848)

Signed-off-by: Rahul Vishwakarma <Rahul.Vishwakarma2@ibm.com>
(cherry picked from commit f7efab5)

[KV-Offloading] Fix tensors_per_block stride (vllm-project#46888)

Signed-off-by: <>
Co-authored-by: Varun Sundar Rabindranath <varun-sundar-rabindranath@h100-01.nemg-001.lab.rdu2.dc.redhat.com>
(cherry picked from commit 798185d)

Fix P/D with DP Supervisor (vllm-project#46628)

Signed-off-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
(cherry picked from commit c5e3c40)

[CI/Build] Fix topk histogram build on SM75 (vllm-project#46550)

Signed-off-by: Mohammad Miadh Angkad <176301910+mmangkad@users.noreply.github.com>
(cherry picked from commit 191826e)

[Bugfix][CI] Update Dockerfile dependency graph PNG (vllm-project#45602)

Signed-off-by: sfeng33 <4florafeng@gmail.com>

[Bugfix][Frontend] Cap fastapi < 0.137 to avoid prometheus-fastapi-in…

…strumentator crash on serve startup

A fresh pip install pulls fastapi 0.137, whose new _IncludedRouter route type
(a BaseRoute with no .path) breaks prometheus-fastapi-instrumentator's route
iteration -> 'vllm serve' dies at startup with:
  AttributeError: '_IncludedRouter' object has no attribute 'path'

requirements/common.txt pinned fastapi[standard]>=0.115.0 with no upper bound.
Cap to <0.137; lift once the instrumentator handles _IncludedRouter
(trallnag/prometheus-fastapi-instrumentator#370).

Signed-off-by: avesed <trevor.lijunlin@gmail.com>