dearwolf/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2025-05-20 02:24:59 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 21

chore: bump grpc limits to 50MB (#5212)

Browse source 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto 2025-04-19 08:53:24 +02:00 • committed by GitHub
parent 8b3f76d8e6
commit 8abecb4a18
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
13 changed files with 161 additions and 31 deletions
Download patch file Download diff file Expand all files Collapse all files

4
backend/cpp/llama/grpc-server.cpp
View file

@ -2644,7 +2644,9 @@ void RunServer(const std::string& server_address) {
ServerBuilder builder;
builder.AddListeningPort(server_address, grpc::InsecureServerCredentials());
builder.RegisterService(&service);
builder.SetMaxMessageSize(50 * 1024 * 1024); // 50MB
builder.SetMaxSendMessageSize(50 * 1024 * 1024); // 50MB
builder.SetMaxReceiveMessageSize(50 * 1024 * 1024); // 50MB
std::unique_ptr<Server> server(builder.BuildAndStart());
std::cout << "Server listening on " << server_address << std::endl;
server->Wait();

7
backend/python/autogptq/backend.py
View file

@ -121,7 +121,12 @@ class BackendServicer(backend_pb2_grpc.BackendServicer):
return (prompt, image_paths)
def serve(address):
server = grpc.server(futures.ThreadPoolExecutor(max_workers=MAX_WORKERS))
server = grpc.server(futures.ThreadPoolExecutor(max_workers=MAX_WORKERS),
options=[
('grpc.max_message_length', 50 * 1024 * 1024), # 50MB
('grpc.max_send_message_length', 50 * 1024 * 1024), # 50MB
('grpc.max_receive_message_length', 50 * 1024 * 1024), # 50MB
])
backend_pb2_grpc.add_BackendServicer_to_server(BackendServicer(), server)
server.add_insecure_port(address)
server.start()

7
backend/python/bark/backend.py
View file

@ -61,7 +61,12 @@ class BackendServicer(backend_pb2_grpc.BackendServicer):
return backend_pb2.Result(success=True)
def serve(address):
server = grpc.server(futures.ThreadPoolExecutor(max_workers=MAX_WORKERS))
server = grpc.server(futures.ThreadPoolExecutor(max_workers=MAX_WORKERS),
options=[
('grpc.max_message_length', 50 * 1024 * 1024), # 50MB
('grpc.max_send_message_length', 50 * 1024 * 1024), # 50MB
('grpc.max_receive_message_length', 50 * 1024 * 1024), # 50MB
])
backend_pb2_grpc.add_BackendServicer_to_server(BackendServicer(), server)
server.add_insecure_port(address)
server.start()

7
backend/python/coqui/backend.py
View file

@ -86,7 +86,12 @@ class BackendServicer(backend_pb2_grpc.BackendServicer):
return backend_pb2.Result(success=True)
def serve(address):
server = grpc.server(futures.ThreadPoolExecutor(max_workers=MAX_WORKERS))
server = grpc.server(futures.ThreadPoolExecutor(max_workers=MAX_WORKERS),
options=[
('grpc.max_message_length', 50 * 1024 * 1024), # 50MB
('grpc.max_send_message_length', 50 * 1024 * 1024), # 50MB
('grpc.max_receive_message_length', 50 * 1024 * 1024), # 50MB
])
backend_pb2_grpc.add_BackendServicer_to_server(BackendServicer(), server)
server.add_insecure_port(address)
server.start()

7
backend/python/diffusers/backend.py
View file

@ -522,7 +522,12 @@ class BackendServicer(backend_pb2_grpc.BackendServicer):
def serve(address):
server = grpc.server(futures.ThreadPoolExecutor(max_workers=MAX_WORKERS))
server = grpc.server(futures.ThreadPoolExecutor(max_workers=MAX_WORKERS),
options=[
('grpc.max_message_length', 50 * 1024 * 1024), # 50MB
('grpc.max_send_message_length', 50 * 1024 * 1024), # 50MB
('grpc.max_receive_message_length', 50 * 1024 * 1024), # 50MB
])
backend_pb2_grpc.add_BackendServicer_to_server(BackendServicer(), server)
server.add_insecure_port(address)
server.start()

7
backend/python/exllama2/backend.py
View file

@ -105,7 +105,12 @@ class BackendServicer(backend_pb2_grpc.BackendServicer):
def serve(address):
server = grpc.server(futures.ThreadPoolExecutor(max_workers=MAX_WORKERS))
server = grpc.server(futures.ThreadPoolExecutor(max_workers=MAX_WORKERS),
options=[
('grpc.max_message_length', 50 * 1024 * 1024), # 50MB
('grpc.max_send_message_length', 50 * 1024 * 1024), # 50MB
('grpc.max_receive_message_length', 50 * 1024 * 1024), # 50MB
])
backend_pb2_grpc.add_BackendServicer_to_server(BackendServicer(), server)
server.add_insecure_port(address)
server.start()

7
backend/python/faster-whisper/backend.py
View file

@ -62,7 +62,12 @@ class BackendServicer(backend_pb2_grpc.BackendServicer):
return backend_pb2.TranscriptResult(segments=resultSegments, text=text)
def serve(address):
server = grpc.server(futures.ThreadPoolExecutor(max_workers=MAX_WORKERS))
server = grpc.server(futures.ThreadPoolExecutor(max_workers=MAX_WORKERS),
options=[
('grpc.max_message_length', 50 * 1024 * 1024), # 50MB
('grpc.max_send_message_length', 50 * 1024 * 1024), # 50MB
('grpc.max_receive_message_length', 50 * 1024 * 1024), # 50MB
])
backend_pb2_grpc.add_BackendServicer_to_server(BackendServicer(), server)
server.add_insecure_port(address)
server.start()

7
backend/python/kokoro/backend.py
View file

@ -99,7 +99,12 @@ class BackendServicer(backend_pb2_grpc.BackendServicer):
return backend_pb2.Result(success=True)
def serve(address):
server = grpc.server(futures.ThreadPoolExecutor(max_workers=MAX_WORKERS))
server = grpc.server(futures.ThreadPoolExecutor(max_workers=MAX_WORKERS),
options=[
('grpc.max_message_length', 50 * 1024 * 1024), # 50MB
('grpc.max_send_message_length', 50 * 1024 * 1024), # 50MB
('grpc.max_receive_message_length', 50 * 1024 * 1024), # 50MB
])
backend_pb2_grpc.add_BackendServicer_to_server(BackendServicer(), server)
server.add_insecure_port(address)
server.start()

7
backend/python/rerankers/backend.py
View file

@ -91,7 +91,12 @@ class BackendServicer(backend_pb2_grpc.BackendServicer):
return backend_pb2.RerankResult(usage=usage, results=results)
def serve(address):
server = grpc.server(futures.ThreadPoolExecutor(max_workers=MAX_WORKERS))
server = grpc.server(futures.ThreadPoolExecutor(max_workers=MAX_WORKERS),
options=[
('grpc.max_message_length', 50 * 1024 * 1024), # 50MB
('grpc.max_send_message_length', 50 * 1024 * 1024), # 50MB
('grpc.max_receive_message_length', 50 * 1024 * 1024), # 50MB
])
backend_pb2_grpc.add_BackendServicer_to_server(BackendServicer(), server)
server.add_insecure_port(address)
server.start()

7
backend/python/transformers/backend.py
View file

@ -559,7 +559,12 @@ class BackendServicer(backend_pb2_grpc.BackendServicer):
async def serve(address):
# Start asyncio gRPC server
server = grpc.aio.server(migration_thread_pool=futures.ThreadPoolExecutor(max_workers=MAX_WORKERS))
server = grpc.aio.server(migration_thread_pool=futures.ThreadPoolExecutor(max_workers=MAX_WORKERS),
options=[
('grpc.max_message_length', 50 * 1024 * 1024), # 50MB
('grpc.max_send_message_length', 50 * 1024 * 1024), # 50MB
('grpc.max_receive_message_length', 50 * 1024 * 1024), # 50MB
])
# Add the servicer to the server
backend_pb2_grpc.add_BackendServicer_to_server(BackendServicer(), server)
# Bind the server to the address

7
backend/python/vllm/backend.py
View file

@ -320,7 +320,12 @@ class BackendServicer(backend_pb2_grpc.BackendServicer):
async def serve(address):
# Start asyncio gRPC server
server = grpc.aio.server(migration_thread_pool=futures.ThreadPoolExecutor(max_workers=MAX_WORKERS))
server = grpc.aio.server(migration_thread_pool=futures.ThreadPoolExecutor(max_workers=MAX_WORKERS),
options=[
('grpc.max_message_length', 50 * 1024 * 1024), # 50MB
('grpc.max_send_message_length', 50 * 1024 * 1024), # 50MB
('grpc.max_receive_message_length', 50 * 1024 * 1024), # 50MB
])
# Add the servicer to the server
backend_pb2_grpc.add_BackendServicer_to_server(BackendServicer(), server)
# Bind the server to the address