diff --git a/server/text_generation_server/server.py b/server/text_generation_server/server.py index 569b6925..a0347cd8 100644 --- a/server/text_generation_server/server.py +++ b/server/text_generation_server/server.py @@ -240,7 +240,11 @@ def serve( interceptors=[ ExceptionInterceptor(), UDSOpenTelemetryAioServerInterceptor(), - ] + ], + options=[ + # Set the maximum possible message length: i32::MAX + ("grpc.max_receive_message_length", (1 << 31) - 1) + ], ) generate_pb2_grpc.add_TextGenerationServiceServicer_to_server( TextGenerationService(model, Cache(), quantize, server_urls), server