LocalAI

mirror of https://github.com/mudler/LocalAI.git synced 2026-07-07 23:07:34 -04:00

Files

Ettore Di Giacinto ebd3dcf3d8 fix(backends): pin grpcio-tools to the installed grpcio in runProtogen

runProtogen installed grpcio-tools unpinned, so the protoc it bundles
stamped backend_pb2.py with the newest Protobuf gencode (7.35.0). When a
backend caps the protobuf runtime lower -- vLLM pins protobuf to 6.33.6 --
the import-time guarantee runtime >= gencode fails:

  google.protobuf.runtime_version.VersionError: Detected incompatible
  Protobuf Gencode/Runtime versions ... gencode 7.35.0 runtime 6.33.6

The backend crashes on `import backend_pb2` before it can serve, which
surfaces to the user as "grpc service not ready". It was mis-reported as a
ROCm/gfx1201 failure in #10718 but is not GPU-specific and affects every
vLLM variant (and any backend that caps protobuf below the latest gencode).

Pin grpcio-tools to the grpcio version the backend already installed --
they release in lockstep -- so the generated gencode stays in step with
the protobuf runtime. Falls back to unpinned when grpcio isn't present.

Closes #10718

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Assisted-by: Claude:claude-opus-4-8 [Claude Code]

2026-07-07 21:08:05 +00:00

template

feat(rocm): bump to 7.x (#9323 )

2026-04-12 08:51:30 +02:00

grpc_auth.py

fix(process): give backend workers a parent-death safety net (#10639 )

2026-07-02 19:16:48 +02:00

libbackend.sh

fix(backends): pin grpcio-tools to the installed grpcio in runProtogen

2026-07-07 21:08:05 +00:00

mlx_utils_test.py

fix(python-backends): parse tool-call arguments for chat templates and split implicit reasoning blocks (#10658 )