mirror/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2026-07-30 09:57:57 -04:00
Code Issues Packages Projects Releases Wiki Activity

fix(vllm): generate protobuf 6 compatible stubs (#10944)

Browse Source 
Pin vLLM protogen to grpcio-tools 1.78.0 so its generated code remains importable by protobuf 6.33.x, and remove stale generated artifacts before regeneration.

Closes #10940

Assisted-by: Codex:gpt-5 [Codex]

Co-authored-by: localai-org-maint-bot <306269227+localai-org-maint-bot@users.noreply.github.com>
This commit is contained in:
localai-org-maint-bot
2026-07-19 08:56:57 +02:00
committed by GitHub
parent 10211948b5
commit 71e98c13a3
2 changed files with 16 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

13
backend/python/common/libbackend.sh
View File

@@ -407,12 +407,18 @@ function runProtogen() {
# protobuf runtime lower (vLLM pins it to 6.33.6), crashing the backend with
# "grpc service not ready" before it ever loads a model. Pinning
# grpcio-tools to the installed grpcio version keeps the gencode in step with
# the runtime. Falls back to unpinned when grpcio isn't installed yet.
# the runtime. Backends whose protobuf runtime trails grpcio can set
# GRPCIO_TOOLS_VERSION to the newest generator their runtime accepts. Falls
# back to unpinned when grpcio isn't installed yet.
# See mudler/LocalAI#10718.
local grpcio_tools_spec="grpcio-tools"
local grpcio_version
grpcio_version="$(python -c 'import importlib.metadata as m; print(m.version("grpcio"))' 2>/dev/null || true)"
if [ -n "${grpcio_version}" ]; then
if [ -n "${GRPCIO_TOOLS_VERSION:-}" ]; then
grpcio_tools_spec="grpcio-tools==${GRPCIO_TOOLS_VERSION}"
else
grpcio_version="$(python -c 'import importlib.metadata as m; print(m.version("grpcio"))' 2>/dev/null || true)"
fi
if [ "${grpcio_tools_spec}" = "grpcio-tools" ] && [ -n "${grpcio_version}" ]; then
grpcio_tools_spec="grpcio-tools==${grpcio_version}"
fi
@@ -422,6 +428,7 @@ function runProtogen() {
uv pip install "${grpcio_tools_spec}"
fi
pushd "${EDIR}" >/dev/null
rm -f backend_pb2.py backend_pb2.pyi backend_pb2_grpc.py
# use the venv python (ensures correct interpreter & sys.path)
python -m grpc_tools.protoc -I../../ -I./ --python_out=. --grpc_python_out=. backend.proto
popd >/dev/null

6
backend/python/vllm/install.sh
View File

@@ -3,6 +3,12 @@ set -e
EXTRA_PIP_INSTALL_FLAGS="--no-build-isolation"
# grpcio 1.82 bundles protoc 7.x, while vLLM's resolved protobuf runtime is
# still 6.33.x. Generate the backend stubs with the newest grpcio-tools release
# that emits protobuf 6.x gencode; the newer grpcio runtime can consume those
# stubs, but protobuf 6.x cannot import 7.x gencode.
export GRPCIO_TOOLS_VERSION="1.78.0"
# Avoid to overcommit the CPU during build
# https://github.com/vllm-project/vllm/issues/20079
# https://docs.vllm.ai/en/v0.8.3/serving/env_vars.html