main

patch-2

update-sampling-api

remove-unwanted-bos

patch-3

patch-1

generic-vlm-chat-format

fix-windows-import-error

fix-embeddings-for-non-embedding-models

expose-libggml

docker

dev-add-rpc

dependabot/pip/starlette-context-gte-0.3.6-and-lt-0.5

dependabot/github_actions/pypa/cibuildwheel-2.23.2

dependabot/github_actions/conda-incubator/setup-miniconda-3.1.1

binary-wheels

batch-processing

add-paligemma-support