master-366-f532972

fix: avoid precision issues on vulkan backend (#980)

master-365-d5b05f7

feat: support independent sampler rng (#978)

master-364-6d6dc1b

fix: make PhotoMakerV2 more robust by image count check (#970)

master-363-199e675

feat: support for --tensor-type-rules on generation modes (#932)

master-362-742a733

feat: add cpu rng (#977)

master-361-e8eb379

fix: typo in --lora-apply-mode help (#972)

master-360-aa44e06

fix: avoid crash with LoRAs and type override (#974)

master-359-6448430

feat: add break pseudo token support (#422)

---------

Co-authored-by: Urs Ganse <urs.ganse@helsinki.fi>

master-358-347710f

feat: support applying LoRA at runtime (#969)

master-357-59ebdf0

chrore: enable Windows ROCm(HIP) build release (#956)

* build: fix missing commit sha in macOS and Ubuntu build zip name

The build workflows for macOS and Ubuntu incorrectly check for the
"main" branch instead of "master" when retrieving the commit hash for
naming the build artifacts.

* build: correct Vulkan SDK installation condition in build workflow

* build: Enable Windows ROCm(HIP) build release

Refer to the build workflow of llama.cpp to add a Windows ROCm (HIP)
build release to the workflow.
Since there are many differences between the HIP build and other
builds, this commit add a separate "windows-latest-cmake-hip" job,
instead of enabling the ROCm matrix entry in the existing Windows
build job.

Main differences include:

- Install ROCm SDK from AMD official installer.
- Add a cache step for ROCm installation and a ccache step for build
  processing, since the HIP build takes much longer time than other
  builds.
- Include the ROCm/HIP artifact in the release assets.