Revert "[V1] DP scale-out (1/N): Use zmq ROUTER/DEALER sockets for in…

…put queue (vllm-project#15906)"

This reverts commit 651cf0f.

[V1][Spec Decode] Update N-gram Proposer Interface (vllm-project#15750)

Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>

[V1][Spec Decode] Update target_logits in place for rejection sampling (

vllm-project#15427)

Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>

[V1] Minor V1 async engine test refactor (vllm-project#15075)

Signed-off-by: andoorve <murali.andoorveedu@mail.utoronto.ca>
Co-authored-by: andoorve <murali.andoorveedu@mail.utoronto.ca>

[Bugfix] Fix LoRA extra vocab size (vllm-project#15047)

Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>

[Bugfix] Make Gemma3 MM V0 only for now (vllm-project#14971)

Signed-off-by: Roger Wang <ywang@roblox.com>

[V1] [Spec Decode] Support random sampling for spec decode (vllm-proj…

…ect#13933)

Co-authored-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>

[Bugfix] Fix deepseekv3 grouped topk error (vllm-project#13474)

Signed-off-by: Chen-XiaoBing <chenxb002@whu.edu.cn>

[Misc] Improve error message for incorrect pynvml (vllm-project#12809)

Signed-off-by: youkaichao <youkaichao@gmail.com>

Disable chunked prefill and/or prefix caching when MLA is enabled (vl…

…lm-project#12642)

From @mgoin in vllm-project#12638

I cannot push to that branch, therefore a new PR to unblock release.

---------

Signed-off-by: mgoin <michael@neuralmagic.com>
Signed-off-by: simon-mo <simon.mo@hey.com>
Co-authored-by: mgoin <michael@neuralmagic.com>