docker: address review round 2 (CI ref freeze, Studio NVRTC amd64, pip-shim edges)
docker-publish.yml: freeze the requested unsloth ref to one sha in the prepare job before the matrix fans out. UNSLOTH_REF / UNSLOTH_STUDIO_REF were raw expressions re-evaluated per base arch leg and in the Studio build, so a mutable branch (the workflow_dispatch default unsloth_ref=main) advancing during the run could bake different unsloth commits under one manifest. Resolve once (same precedence: dispatch input, else pushed tag, else triggering sha, else main; ls-remote a branch/tag to a sha, mirroring the zoo/notebooks steps) and read needs.prepare.outputs.unsloth_ref everywhere. Dockerfile.studio: run the Studio venv NVRTC cu13 swap on both arches, not arm64 only. amd64 sm_103 (B300/GB300) needs cu13 NVRTC just as arm64 sm_121 does, and the CUDA dedup never touches cuda_nvrtc, so an amd64 Studio venv would otherwise keep its bundled cu12.8 libnvrtc and fail NVRTC/jiterator JIT on compute_103. The base cu13 layer installs cuda-nvrtc-13-0 on both arches, so the target .so.13 exists here regardless of TARGETARCH. unsloth_pip_shim.py: close three ways a protected package slipped past _KEEP. Treat -e/--editable as a value-taking flag paired with its target and drop both when the target is protected (was leaving a dangling -e that failed the cell); filter -P/--upgrade-package values through _KEEP (a named baked package could be refreshed while installing another target); and parse the PEP 427 distribution name out of a wheel URL/path so a bare `pip install https://.../torch-...whl` drops instead of reinstalling the baked torch. Non-protected editables, upgrade selectors, and wheels are unchanged. Adds tests/python/test_unsloth_pip_shim.py (18 regression tests, exec captured via a patched os.execv).
This commit is contained in:
Daniel Han
parent
386d3a7c74
commit
d4dc8b6391
4 changed files with 369 additions and 25 deletions
59
.github/workflows/docker-publish.yml
vendored
59
.github/workflows/docker-publish.yml
vendored
|
|
@ -89,10 +89,12 @@ jobs:
|
|||
contents: read
|
||||
outputs:
|
||||
llama_tag: ${{ steps.llama.outputs.tag }}
|
||||
# One zoo ref + one notebooks commit, resolved here so BOTH arch legs of
|
||||
# the base build (and the Studio build) bake the identical bits. Resolving
|
||||
# them per-leg would let upstream advance between the amd64 and arm64
|
||||
# builds, putting different content under one published tag.
|
||||
# One unsloth ref + one zoo ref + one notebooks commit, resolved here so
|
||||
# BOTH arch legs of the base build AND the Studio build bake the identical
|
||||
# bits. Resolving them per-leg would let upstream advance between the amd64
|
||||
# and arm64 builds (or between the base and Studio builds), putting
|
||||
# different content under one published tag.
|
||||
unsloth_ref: ${{ steps.unsloth_ref.outputs.ref }}
|
||||
zoo_ref: ${{ steps.zoo_ref.outputs.ref }}
|
||||
notebooks_commit: ${{ steps.notebooks.outputs.commit }}
|
||||
steps:
|
||||
|
|
@ -110,6 +112,36 @@ jobs:
|
|||
echo "tag=${TAG:-latest}" >> "$GITHUB_OUTPUT"
|
||||
echo "llama.cpp prebuilt tag: ${TAG:-latest}"
|
||||
|
||||
# Freeze the requested unsloth ref to ONE concrete sha before the matrix
|
||||
# fans out, so both base arch legs AND the Studio build bake the identical
|
||||
# unsloth commit even when the requested ref is a mutable branch (the
|
||||
# workflow_dispatch default is unsloth_ref=main) that advances during the
|
||||
# ~4h base + Studio run. Same requested-ref precedence the inline build-arg
|
||||
# used: the dispatch input wins (default main), else the pushed tag, else
|
||||
# the triggering commit sha, else main. A 40-char sha (branch/schedule
|
||||
# push) is already frozen; a branch/tag is resolved via ls-remote, exactly
|
||||
# like the zoo and notebooks steps, falling back to the bare ref on a
|
||||
# lookup miss so the Dockerfile can still fetch it by name.
|
||||
- name: Resolve unsloth ref
|
||||
id: unsloth_ref
|
||||
env:
|
||||
INPUT_REF: ${{ github.event.inputs.unsloth_ref }}
|
||||
TAG_REF: ${{ startsWith(github.ref, 'refs/tags/') && github.ref_name || '' }}
|
||||
PUSH_SHA: ${{ github.sha }}
|
||||
run: |
|
||||
REF="$INPUT_REF"
|
||||
[ -n "$REF" ] || REF="$TAG_REF"
|
||||
[ -n "$REF" ] || REF="$PUSH_SHA"
|
||||
REF="${REF:-main}"
|
||||
if printf '%s' "$REF" | grep -Eq '^[0-9a-f]{40}$'; then
|
||||
SHA="$REF"
|
||||
else
|
||||
SHA="$(git ls-remote https://github.com/unslothai/unsloth "$REF" | awk 'NR==1{print $1}')"
|
||||
[ -n "$SHA" ] || SHA="$REF"
|
||||
fi
|
||||
echo "ref=${SHA}" >> "$GITHUB_OUTPUT"
|
||||
echo "unsloth ref: ${SHA}"
|
||||
|
||||
# Mirror the unsloth tag into the zoo ONLY when that tag actually exists
|
||||
# there. unsloth's v* tags are Studio releases the zoo never cuts (the zoo
|
||||
# repo currently has no tags at all), so blindly mirroring github.ref_name
|
||||
|
|
@ -242,10 +274,12 @@ jobs:
|
|||
# NOTE: keep prose OUT of build-args -- docker/build-push-action
|
||||
# forwards every non-empty line verbatim, so a leading-# line would be
|
||||
# passed as a bogus --build-arg. Explanations live here instead:
|
||||
# UNSLOTH_REF: workflow-dispatch honours the explicit input; tag
|
||||
# pushes bake the tag's source ref (e.g. v1.2.3) so the published
|
||||
# image actually contains that release; branch + scheduled runs bake
|
||||
# the triggering commit SHA; any other event falls back to main.
|
||||
# UNSLOTH_REF (from the prepare job): resolved to ONE sha before the
|
||||
# matrix fans out, so both arch legs and the Studio build bake the
|
||||
# identical unsloth commit even if a mutable branch (dispatch's
|
||||
# unsloth_ref=main default) advances mid-run. Same requested-ref
|
||||
# precedence as before: dispatch input, else the pushed tag, else
|
||||
# the triggering commit sha, else main.
|
||||
# UNSLOTH_ZOO_REF (from the prepare job): explicit dispatch input,
|
||||
# else the pushed tag IF the zoo repo has it, else main -- a branch
|
||||
# SHA does not exist in the zoo repo. Resolved once in `prepare` and
|
||||
|
|
@ -257,7 +291,7 @@ jobs:
|
|||
CUDA_VERSION=12.8.1
|
||||
UBUNTU_VERSION=24.04
|
||||
PYTHON_VERSION=3.12
|
||||
UNSLOTH_REF=${{ github.event.inputs.unsloth_ref || (startsWith(github.ref, 'refs/tags/') && github.ref_name) || github.sha || 'main' }}
|
||||
UNSLOTH_REF=${{ needs.prepare.outputs.unsloth_ref }}
|
||||
UNSLOTH_ZOO_REF=${{ needs.prepare.outputs.zoo_ref }}
|
||||
LLAMA_PREBUILT_TAG=${{ needs.prepare.outputs.llama_tag }}
|
||||
UNSLOTH_NOTEBOOKS_REF=${{ needs.prepare.outputs.notebooks_commit }}
|
||||
|
|
@ -430,15 +464,16 @@ jobs:
|
|||
cache-from: type=gha,scope=studio-${{ matrix.platform }}
|
||||
cache-to: type=gha,scope=studio-${{ matrix.platform }},mode=min
|
||||
outputs: type=image,name=${{ env.REGISTRY }}/${{ env.IMAGE_NAME }},push-by-digest=true,name-canonical=true,push=true
|
||||
# UNSLOTH_STUDIO_REF mirrors the base job's UNSLOTH_REF resolution so the
|
||||
# Studio tree matches the unsloth baked into the base venv.
|
||||
# UNSLOTH_STUDIO_REF is the SAME resolved unsloth sha the base build
|
||||
# baked (needs.prepare.outputs.unsloth_ref), so the Studio tree matches
|
||||
# the unsloth in the base venv even if the branch moved mid-run.
|
||||
# UNSLOTH_STUDIO_ZOO_REF is the SAME resolved zoo ref the base build
|
||||
# baked, so install.sh --local overlays the Studio venv with that zoo
|
||||
# instead of always tracking main. (Prose stays out of build-args --
|
||||
# forwarded lines must be KEY=VALUE only.)
|
||||
build-args: |
|
||||
BASE_IMAGE=${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}@${{ needs.merge.outputs.digest }}
|
||||
UNSLOTH_STUDIO_REF=${{ github.event.inputs.unsloth_ref || (startsWith(github.ref, 'refs/tags/') && github.ref_name) || github.sha || 'main' }}
|
||||
UNSLOTH_STUDIO_REF=${{ needs.prepare.outputs.unsloth_ref }}
|
||||
UNSLOTH_STUDIO_ZOO_REF=${{ needs.prepare.outputs.zoo_ref }}
|
||||
|
||||
- name: Export digest
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue