mirror of
https://github.com/mudler/LocalAI.git
synced 2026-09-15 15:52:31 -04:00
fix(ci): unbreak the e2e build and the darwin vllm-metal pin (#11849)
Two independent breakages on master make every open pull request red, for reasons unrelated to the changes under review. The e2e backend suite stopped compiling. Reply.message is `bytes` in backend.proto, so res.GetMessage() returns []byte, and strings.ToUpper wants a string. Every other call site in the file already converts. tests/e2e-backends sits behind a build tag, so `go build ./...` never compiled it and the breakage reached master unnoticed. The darwin vllm build stopped resolving. Upstream vllm-metal deleted its old dev tags and re-versioned to track the vLLM release it targets, so the pinned wheel 404s. The coupled vLLM release also moved out of upstream's install.sh into .github/vllm-release-tag.commit, and the wheel's platform tag moved from macosx_11_0 to macosx_15_0. Read the wheel name from the release's own asset listing rather than composing it from a hardcoded platform segment, so a platform-tag change cannot silently 404 again, and resolve the vLLM version from the new metadata file with a fallback to the legacy installer. The bump script and the extractor learn the same two-source lookup, so the next nightly run converges on the pin checked in here instead of reintroducing the break. Assisted-by: Claude:claude-opus-5 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Co-authored-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
1 parent
9901103aac
commit
7a234473e8
5 files changed
+66
-20
No files matched your search
@@ -3,9 +3,9 @@
|
||||
# darwin (Apple Silicon) install path. The macOS/Metal build
|
||||
# (backend/python/vllm/install.sh, Darwin branch) installs vllm-metal, which is
|
||||
# version-locked to a specific vLLM source release. install.sh derives that vLLM
|
||||
# version at build time from vllm-metal's own installer at the pinned
|
||||
# tag, so there is only ONE value to bump here -- mirroring bump_vllm_wheel.sh,
|
||||
# which bumps the Linux cu130 wheel pin.
|
||||
# version, and the wheel asset name, at build time from the pinned tag, so there
|
||||
# is only ONE value to bump here -- mirroring bump_vllm_wheel.sh, which bumps the
|
||||
# Linux cu130 wheel pin.
|
||||
#
|
||||
# This deliberately tracks vllm-project/vllm-metal, NOT vllm-project/vllm: the
|
||||
# darwin build can only use the exact vLLM version vllm-metal supports, so it may
|
||||
@@ -23,15 +23,20 @@ if [ -z "$FILE" ] || [ -z "$REPO" ] || [ -z "$VAR" ]; then
|
||||
exit 1
|
||||
fi
|
||||
|
||||
# vllm-metal ships frequent dev releases, all flagged as non-prerelease, so
|
||||
# /releases/latest returns the newest one (with its cp312 wheel asset).
|
||||
# vllm-metal ships frequent .dev releases, flagged as prereleases, alongside the
|
||||
# stable ones. /releases/latest skips the prereleases and returns the newest
|
||||
# stable tag, which is what darwin should pin: upstream deletes and re-cuts .dev
|
||||
# tags, and a pin to a deleted tag 404s the whole build.
|
||||
LATEST_TAG=$(gh_curl -H "Accept: application/vnd.github+json" \
|
||||
"https://api.github.com/repos/$REPO/releases/latest" \
|
||||
| python3 -c "import json,sys; print(json.load(sys.stdin)['tag_name'])")
|
||||
|
||||
# The coupled vLLM source version lives in vllm-metal's installer at that tag.
|
||||
NEW_VLLM_VERSION=$(gh_curl \
|
||||
"https://raw.githubusercontent.com/$REPO/$LATEST_TAG/install.sh" \
|
||||
# The coupled vLLM release lives in .github/vllm-release-tag.commit at that tag
|
||||
# (since vllm-metal 0.28); releases predating that file pinned it inline in their
|
||||
# own install.sh. The extractor reads both forms.
|
||||
NEW_VLLM_VERSION=$( { gh_curl \
|
||||
"https://raw.githubusercontent.com/$REPO/$LATEST_TAG/.github/vllm-release-tag.commit" \
|
||||
|| gh_curl "https://raw.githubusercontent.com/$REPO/$LATEST_TAG/install.sh"; } \
|
||||
| "$(dirname "${BASH_SOURCE[0]}")/../scripts/lib/extract-vllm-metal-version.sh")
|
||||
|
||||
if [ -z "$LATEST_TAG" ] || [ -z "$NEW_VLLM_VERSION" ]; then
|
||||
|
||||
@@ -119,14 +119,18 @@ if [ "$(uname -s)" = "Darwin" ]; then
|
||||
# can rewrite it. Darwin therefore follows vllm-metal and can lag the Linux
|
||||
# vllm pin (requirements-cublas13-after.txt, bumped independently against
|
||||
# vllm/vllm) until vllm-metal supports a newer vLLM.
|
||||
VLLM_METAL_VERSION="v0.3.0.dev20260818075955"
|
||||
VLLM_METAL_VERSION="v0.28.0"
|
||||
|
||||
# The coupled vLLM source version is whatever this vllm-metal release builds
|
||||
# against. Derive it from
|
||||
# the PINNED tag rather than hardcoding a second value that could drift. The
|
||||
# tag is immutable, so this stays reproducible across rebuilds.
|
||||
VLLM_VERSION=$(curl -fsSL "https://raw.githubusercontent.com/vllm-project/vllm-metal/${VLLM_METAL_VERSION}/install.sh" \
|
||||
| "$backend_dir/../../../scripts/lib/extract-vllm-metal-version.sh")
|
||||
# against. Derive it from the PINNED tag rather than hardcoding a second value
|
||||
# that could drift. The tag is immutable, so this stays reproducible across
|
||||
# rebuilds. Since vllm-metal 0.28 the coupling is declared in
|
||||
# .github/vllm-release-tag.commit; older releases pinned it inline in their
|
||||
# own install.sh, so fall back to that. The extractor reads both forms.
|
||||
_vllm_metal_raw="https://raw.githubusercontent.com/vllm-project/vllm-metal/${VLLM_METAL_VERSION}"
|
||||
VLLM_VERSION=$( { curl -fsSL "${_vllm_metal_raw}/.github/vllm-release-tag.commit" \
|
||||
|| curl -fsSL "${_vllm_metal_raw}/install.sh"; } \
|
||||
| "$backend_dir/../../../scripts/lib/extract-vllm-metal-version.sh" || true)
|
||||
if [ -z "${VLLM_VERSION}" ]; then
|
||||
echo "ERROR: could not derive the vLLM version from vllm-metal ${VLLM_METAL_VERSION}" >&2
|
||||
exit 1
|
||||
@@ -153,10 +157,18 @@ if [ "$(uname -s)" = "Darwin" ]; then
|
||||
# 2) Install the prebuilt vllm-metal wheel for the PINNED release. It pulls
|
||||
# mlx / mlx-metal as deps and registers the `metal` platform plugin that
|
||||
# backend.py resolves to at engine-init time. Build the release-asset URL
|
||||
# deterministically (tag + the cp312/arm64 wheel name) rather than querying
|
||||
# api.github.com, whose unauthenticated rate limit (60/hr per IP) 403s on
|
||||
# shared CI runners. The wheel version is the tag without its leading 'v'.
|
||||
_metal_wheel="vllm_metal-${VLLM_METAL_VERSION#v}-cp312-cp312-macosx_11_0_arm64.whl"
|
||||
# from the release's OWN asset listing rather than composing it from a
|
||||
# hardcoded platform tag: upstream raised its macOS deployment target
|
||||
# (macosx_11_0 -> macosx_15_0) and every composed URL started to 404.
|
||||
# expanded_assets is the plain release page, not api.github.com, whose
|
||||
# unauthenticated rate limit (60/hr per IP) 403s on shared CI runners.
|
||||
# The wheel version is the tag without its leading 'v'.
|
||||
_metal_wheel=$(curl -fsSL "https://github.com/vllm-project/vllm-metal/releases/expanded_assets/${VLLM_METAL_VERSION}" \
|
||||
| grep -oE "vllm_metal-${VLLM_METAL_VERSION#v}-cp312-cp312-[A-Za-z0-9_]+\.whl" | head -1 || true)
|
||||
if [ -z "${_metal_wheel}" ]; then
|
||||
echo "ERROR: no cp312 wheel asset on vllm-metal release ${VLLM_METAL_VERSION}" >&2
|
||||
exit 1
|
||||
fi
|
||||
_metal_wheel_url="https://github.com/vllm-project/vllm-metal/releases/download/${VLLM_METAL_VERSION}/${_metal_wheel}"
|
||||
echo "Installing vllm-metal wheel: ${_metal_wheel_url}"
|
||||
uv pip install "${_metal_wheel_url}"
|
||||
|
||||
@@ -21,6 +21,17 @@ assert_version "0.26.0" ' local vllm_v="0.26.0"'
|
||||
assert_version "0.26.0" 'VLLM_VERSION="0.26.0"'
|
||||
assert_version "0.26.1" ' VLLM_VERSION = "0.26.1" # comment'
|
||||
|
||||
# .github/vllm-release-tag.commit form: a lone vLLM release tag.
|
||||
assert_version "0.28.0" 'v0.28.0'
|
||||
assert_version "0.28.0" '0.28.0'
|
||||
assert_version "0.28.0" ' v0.28.0 '
|
||||
|
||||
# A whole upstream installer must still yield the inline pin, not a version-like
|
||||
# fragment of some other line.
|
||||
assert_version "0.26.0" 'set -e
|
||||
vllm_wheel="vllm-1.2.3-cp312.whl"
|
||||
VLLM_VERSION="0.26.0"'
|
||||
|
||||
if printf '%s\n' 'VLLM_VERSION="not-a-version"' | "$extractor"; then
|
||||
echo "malformed versions must be rejected" >&2
|
||||
exit 1
|
||||
@@ -30,3 +41,13 @@ if printf '%s\n' 'VLLM_VERSION="0.26.0"garbage' | "$extractor"; then
|
||||
echo "trailing assignment content must be rejected" >&2
|
||||
exit 1
|
||||
fi
|
||||
|
||||
if printf '%s\n' 'not-a-tag' | "$extractor"; then
|
||||
echo "malformed release tags must be rejected" >&2
|
||||
exit 1
|
||||
fi
|
||||
|
||||
if printf '%s\n' 'vllm-1.2.3-cp312.whl' | "$extractor"; then
|
||||
echo "a version embedded in a longer line must be rejected" >&2
|
||||
exit 1
|
||||
fi
|
||||
@@ -1,5 +1,13 @@
|
||||
#!/bin/bash
|
||||
set -euo pipefail
|
||||
|
||||
grep -m1 -oE '^[[:space:]]*(local[[:space:]]+)?(vllm_v|VLLM_VERSION)[[:space:]]*=[[:space:]]*"[0-9]+\.[0-9]+\.[0-9]+"[[:space:]]*(#.*)?$' \
|
||||
# Print the bare X.Y.Z vLLM version a vllm-metal release builds against, reading
|
||||
# whichever form the release declares it in on stdin:
|
||||
#
|
||||
# * .github/vllm-release-tag.commit -- a lone "vX.Y.Z" vLLM release tag. This is
|
||||
# the source of truth since vllm-metal 0.28, which also re-versioned the
|
||||
# project so its own version tracks the vLLM version it targets.
|
||||
# * install.sh -- releases predating that file pinned VLLM_VERSION="X.Y.Z"
|
||||
# (earlier still: vllm_v="X.Y.Z") inline in their installer.
|
||||
grep -m1 -oE '^[[:space:]]*((local[[:space:]]+)?(vllm_v|VLLM_VERSION)[[:space:]]*=[[:space:]]*"[0-9]+\.[0-9]+\.[0-9]+"[[:space:]]*(#.*)?|v?[0-9]+\.[0-9]+\.[0-9]+[[:space:]]*)$' \
|
||||
| grep -oE '[0-9]+\.[0-9]+\.[0-9]+'
|
||||
@@ -473,7 +473,7 @@ var _ = Describe("Backend container", Ordered, func() {
|
||||
Expect(res.GetPromptTokens()).To(BeNumerically(">", 128),
|
||||
"prompt is too short to span multiple prefill batches; this spec would not prove anything")
|
||||
}
|
||||
Expect(strings.ToUpper(res.GetMessage())).To(ContainSubstring(needle),
|
||||
Expect(strings.ToUpper(string(res.GetMessage()))).To(ContainSubstring(needle),
|
||||
"a long prompt lost information the model repeats correctly from a short one - "+
|
||||
"batched prefill is corrupting state (check the backend's device architecture flags)")
|
||||
GinkgoWriter.Printf("LongPrefill: prompt_tokens=%d tokens=%d msg=%q\n",
|
||||
|
||||
Reference in new issue
Block a user