pr-set.json

{
  "_doc": [
    "ggml-org/llama.cpp or unslothai/llama.cpp PRs to merge into the nightly prebuilds. Each entry",
    "pins an exact commit -- copy the url of the commit you reviewed from the PR's commits tab:",
    "  https://github.com/ggml-org/llama.cpp/pull/15926/commits/59a3d0cb8f611aa3110ecea3d0afd16b1b18ee06",
    "Only that commit is built, even if the author keeps pushing; update the pin to take newer code.",
    "An empty list is a plain upstream build.",
    "Closed and merged PRs are STILL merged in. Upstream tags lag their merges and the base is",
    "aged a further UNSLOTH_LLAMA_MIN_RELEASE_AGE_HOURS, so a pin dropped on merge leaves its arch",
    "in neither the base nor the mix. Once the base tag contains the commit the merge is an empty",
    "no-op ONLY if upstream took the PR as a merge commit. Upstream usually squashes, and a squash",
    "is not an ancestor of the pinned commit, so the merge re-applies code the base already has and",
    "the whole build stops on an unresolvable conflict. Delete the entry once a base tag carries the",
    "work, do not wait for it to rot away. A closed-unmerged pin ships code upstream",
    "declined -- the resolve log warns, but nothing else stops it, so prune those deliberately.",
    "Use {\"url\": \"...\", \"required\": false} for an entry that should be skipped once it is not open.",
    "Merging an unslothai PR into fork master drops it from the nightly (the tree is the upstream",
    "tag + pins), so keep its pin listed until the change lands upstream."
  ],
  "prs": [
    "https://github.com/ggml-org/llama.cpp/pull/24423/commits/168b21adfb36f740989284c9d73a5ccabf679e46",
    "https://github.com/ggml-org/llama.cpp/pull/25731/commits/946fc11d1afb1e6cd316e853f1b23487754a74b9",
    "https://github.com/unslothai/llama.cpp/pull/70/commits/883f2c9ba78f3847148454adf025da29385fff3e",
    "https://github.com/unslothai/llama.cpp/pull/61/commits/46cbf0e95786fe8f5b7c0e86d57aaf8f8eceea7f",
    "https://github.com/unslothai/llama.cpp/pull/95/commits/3db8cb5b2e9bf291057b9f19960e8601a162da81",
    "https://github.com/ggml-org/llama.cpp/pull/27754/commits/b9b8207fcfc2962093b9466df7af4ff29c2a81ef",
    "https://github.com/unslothai/llama.cpp/pull/137/commits/4e1865e34ec5f6ca39403215c89129c13731be70",
    "https://github.com/unslothai/llama.cpp/pull/158/commits/abfc45b9cb21eae4848cb82196e659f42c9a8341",
    "https://github.com/unslothai/llama.cpp/pull/157/commits/6c6da89266ba7839d825c9997782af4f4d26b81b",
    "https://github.com/unslothai/llama.cpp/pull/149/commits/b65a2dce12c14a489e19a059cb6ee59112f1b733",
    "https://github.com/unslothai/llama.cpp/pull/144/commits/a9e9c3c5fed8a0bb5cc617532d0d16b8f59c13e0",
    "https://github.com/unslothai/llama.cpp/pull/152/commits/b2b5ed9ff86427a530b762a45d3fdbd453bcd4e8",
    "https://github.com/unslothai/llama.cpp/pull/176/commits/09ce1a4d2939844e211f7b4d30a296f4c1aed9a8",
    "https://github.com/unslothai/llama.cpp/pull/210/commits/ae195390599e1ea8c4dbcc6b1d8ec77f5db90c3a"
  ]
}