fix: cleanup

2022-10-08 12:34:25 +02:00 · 2022-10-08 12:34:25 +02:00 · 1d986983d5
parent 295831a481
commit 1d986983d5
18 changed files with 2 additions and 424 deletions
--- a/server/.DS_Store
+++ b/server/.DS_Store
--- a/server/bloom_inference/.DS_Store
+++ b/server/bloom_inference/.DS_Store
--- a/server/bloom_inference/pycache/init.cpython-39.pyc
+++ b/server/bloom_inference/pycache/init.cpython-39.pyc
--- a/server/bloom_inference/pycache/cache.cpython-39.pyc
+++ b/server/bloom_inference/pycache/cache.cpython-39.pyc
--- a/server/bloom_inference/pycache/model.cpython-39.pyc
+++ b/server/bloom_inference/pycache/model.cpython-39.pyc
--- a/server/bloom_inference/pycache/server.cpython-39.pyc
+++ b/server/bloom_inference/pycache/server.cpython-39.pyc
--- a/server/bloom_inference/pycache/shard_model.cpython-39.pyc
+++ b/server/bloom_inference/pycache/shard_model.cpython-39.pyc
--- a/server/bloom_inference/pycache/utils.cpython-39.pyc
+++ b/server/bloom_inference/pycache/utils.cpython-39.pyc
--- a/server/bloom_inference/pb/.gitignore
+++ b/server/bloom_inference/pb/.gitignore
@ -0,0 +1,2 @@
+*.py
+*.py-e
--- a/server/bloom_inference/pb/init.py
+++ b/server/bloom_inference/pb/init.py
--- a/server/bloom_inference/pb/init.py-e
+++ b/server/bloom_inference/pb/init.py-e
--- a/server/bloom_inference/pb/pycache/init.cpython-39.pyc
+++ b/server/bloom_inference/pb/pycache/init.cpython-39.pyc
--- a/server/bloom_inference/pb/pycache/generate_pb2.cpython-39.pyc
+++ b/server/bloom_inference/pb/pycache/generate_pb2.cpython-39.pyc
--- a/server/bloom_inference/pb/pycache/generate_pb2_grpc.cpython-39.pyc
+++ b/server/bloom_inference/pb/pycache/generate_pb2_grpc.cpython-39.pyc
--- a/server/bloom_inference/pb/generate_pb2.py
+++ b/server/bloom_inference/pb/generate_pb2.py
@ -1,43 +0,0 @@
-# -*- coding: utf-8 -*-
-# Generated by the protocol buffer compiler.  DO NOT EDIT!
-# source: generate.proto
-"""Generated protocol buffer code."""
-from google.protobuf.internal import builder as _builder
-from google.protobuf import descriptor as _descriptor
-from google.protobuf import descriptor_pool as _descriptor_pool
-from google.protobuf import symbol_database as _symbol_database
-# @@protoc_insertion_point(imports)
-
-_sym_db = _symbol_database.Default()
-
-
-
-
-DESCRIPTOR = _descriptor_pool.Default().AddSerializedFile(b'\n\x0egenerate.proto\x12\x0bgenerate.v1\"(\n\x18ServiceDiscoveryResponse\x12\x0c\n\x04urls\x18\x01 \x03(\t\"^\n\x16LogitsWarperParameters\x12\x13\n\x0btemperature\x18\x01 \x01(\x02\x12\r\n\x05top_k\x18\x02 \x01(\r\x12\r\n\x05top_p\x18\x03 \x01(\x02\x12\x11\n\tdo_sample\x18\x04 \x01(\x08\"v\n\x07Request\x12\n\n\x02id\x18\x01 \x01(\x04\x12\x0e\n\x06inputs\x18\x02 \x01(\t\x12\x37\n\nparameters\x18\x03 \x01(\x0b\x32#.generate.v1.LogitsWarperParameters\x12\x16\n\x0emax_new_tokens\x18\x04 \x01(\r\";\n\x05\x42\x61tch\x12\n\n\x02id\x18\x01 \x01(\x04\x12&\n\x08requests\x18\x02 \x03(\x0b\x32\x14.generate.v1.Request\"\x7f\n\x0b\x42\x61tchCached\x12\n\n\x02id\x18\x01 \x01(\x04\x12\x13\n\x0brequest_ids\x18\x02 \x03(\x04\x12\x18\n\x10\x62\x61tch_cached_ids\x18\x03 \x03(\x04\x12\x18\n\x10total_batch_size\x18\x04 \x01(\r\x12\x1b\n\x13max_sequence_length\x18\x05 \x01(\r\"0\n\x12\x46inishedGeneration\x12\n\n\x02id\x18\x01 \x01(\x04\x12\x0e\n\x06output\x18\x02 \x01(\t\"F\n\nCacheEntry\x12\n\n\x02id\x18\x01 \x01(\x04\x12\x13\n\x0brequest_ids\x18\x02 \x03(\x04\x12\x17\n\x0fsequence_length\x18\x03 \x01(\r\"\x80\x01\n\x08Response\x12\x31\n\x08\x66inished\x18\x01 \x03(\x0b\x32\x1f.generate.v1.FinishedGeneration\x12\x31\n\x0b\x63\x61\x63he_entry\x18\x02 \x01(\x0b\x32\x17.generate.v1.CacheEntryH\x00\x88\x01\x01\x42\x0e\n\x0c_cache_entry\"\x07\n\x05\x45mpty2\x94\x02\n\x0eTextGeneration\x12O\n\x10ServiceDiscovery\x12\x12.generate.v1.Empty\x1a%.generate.v1.ServiceDiscoveryResponse\"\x00\x12\x34\n\nClearCache\x12\x12.generate.v1.Empty\x1a\x12.generate.v1.Empty\x12\x35\n\x08Generate\x12\x12.generate.v1.Batch\x1a\x15.generate.v1.Response\x12\x44\n\x11GenerateWithCache\x12\x18.generate.v1.BatchCached\x1a\x15.generate.v1.Responseb\x06proto3')
-
-_builder.BuildMessageAndEnumDescriptors(DESCRIPTOR, globals())
-_builder.BuildTopDescriptorsAndMessages(DESCRIPTOR, 'generate_pb2', globals())
-if _descriptor._USE_C_DESCRIPTORS == False:
-
-  DESCRIPTOR._options = None
-  _SERVICEDISCOVERYRESPONSE._serialized_start=31
-  _SERVICEDISCOVERYRESPONSE._serialized_end=71
-  _LOGITSWARPERPARAMETERS._serialized_start=73
-  _LOGITSWARPERPARAMETERS._serialized_end=167
-  _REQUEST._serialized_start=169
-  _REQUEST._serialized_end=287
-  _BATCH._serialized_start=289
-  _BATCH._serialized_end=348
-  _BATCHCACHED._serialized_start=350
-  _BATCHCACHED._serialized_end=477
-  _FINISHEDGENERATION._serialized_start=479
-  _FINISHEDGENERATION._serialized_end=527
-  _CACHEENTRY._serialized_start=529
-  _CACHEENTRY._serialized_end=599
-  _RESPONSE._serialized_start=602
-  _RESPONSE._serialized_end=730
-  _EMPTY._serialized_start=732
-  _EMPTY._serialized_end=739
-  _TEXTGENERATION._serialized_start=742
-  _TEXTGENERATION._serialized_end=1018
-# @@protoc_insertion_point(module_scope)
--- a/server/bloom_inference/pb/generate_pb2.py-e
+++ b/server/bloom_inference/pb/generate_pb2.py-e
@ -1,43 +0,0 @@
-# -*- coding: utf-8 -*-
-# Generated by the protocol buffer compiler.  DO NOT EDIT!
-# source: generate.proto
-"""Generated protocol buffer code."""
-from google.protobuf.internal import builder as _builder
-from google.protobuf import descriptor as _descriptor
-from google.protobuf import descriptor_pool as _descriptor_pool
-from google.protobuf import symbol_database as _symbol_database
-# @@protoc_insertion_point(imports)
-
-_sym_db = _symbol_database.Default()
-
-
-
-
-DESCRIPTOR = _descriptor_pool.Default().AddSerializedFile(b'\n\x0egenerate.proto\x12\x0bgenerate.v1\"(\n\x18ServiceDiscoveryResponse\x12\x0c\n\x04urls\x18\x01 \x03(\t\"^\n\x16LogitsWarperParameters\x12\x13\n\x0btemperature\x18\x01 \x01(\x02\x12\r\n\x05top_k\x18\x02 \x01(\r\x12\r\n\x05top_p\x18\x03 \x01(\x02\x12\x11\n\tdo_sample\x18\x04 \x01(\x08\"v\n\x07Request\x12\n\n\x02id\x18\x01 \x01(\x04\x12\x0e\n\x06inputs\x18\x02 \x01(\t\x12\x37\n\nparameters\x18\x03 \x01(\x0b\x32#.generate.v1.LogitsWarperParameters\x12\x16\n\x0emax_new_tokens\x18\x04 \x01(\r\";\n\x05\x42\x61tch\x12\n\n\x02id\x18\x01 \x01(\x04\x12&\n\x08requests\x18\x02 \x03(\x0b\x32\x14.generate.v1.Request\"\x7f\n\x0b\x42\x61tchCached\x12\n\n\x02id\x18\x01 \x01(\x04\x12\x13\n\x0brequest_ids\x18\x02 \x03(\x04\x12\x18\n\x10\x62\x61tch_cached_ids\x18\x03 \x03(\x04\x12\x18\n\x10total_batch_size\x18\x04 \x01(\r\x12\x1b\n\x13max_sequence_length\x18\x05 \x01(\r\"0\n\x12\x46inishedGeneration\x12\n\n\x02id\x18\x01 \x01(\x04\x12\x0e\n\x06output\x18\x02 \x01(\t\"F\n\nCacheEntry\x12\n\n\x02id\x18\x01 \x01(\x04\x12\x13\n\x0brequest_ids\x18\x02 \x03(\x04\x12\x17\n\x0fsequence_length\x18\x03 \x01(\r\"\x80\x01\n\x08Response\x12\x31\n\x08\x66inished\x18\x01 \x03(\x0b\x32\x1f.generate.v1.FinishedGeneration\x12\x31\n\x0b\x63\x61\x63he_entry\x18\x02 \x01(\x0b\x32\x17.generate.v1.CacheEntryH\x00\x88\x01\x01\x42\x0e\n\x0c_cache_entry\"\x07\n\x05\x45mpty2\x94\x02\n\x0eTextGeneration\x12O\n\x10ServiceDiscovery\x12\x12.generate.v1.Empty\x1a%.generate.v1.ServiceDiscoveryResponse\"\x00\x12\x34\n\nClearCache\x12\x12.generate.v1.Empty\x1a\x12.generate.v1.Empty\x12\x35\n\x08Generate\x12\x12.generate.v1.Batch\x1a\x15.generate.v1.Response\x12\x44\n\x11GenerateWithCache\x12\x18.generate.v1.BatchCached\x1a\x15.generate.v1.Responseb\x06proto3')
-
-_builder.BuildMessageAndEnumDescriptors(DESCRIPTOR, globals())
-_builder.BuildTopDescriptorsAndMessages(DESCRIPTOR, 'generate_pb2', globals())
-if _descriptor._USE_C_DESCRIPTORS == False:
-
-  DESCRIPTOR._options = None
-  _SERVICEDISCOVERYRESPONSE._serialized_start=31
-  _SERVICEDISCOVERYRESPONSE._serialized_end=71
-  _LOGITSWARPERPARAMETERS._serialized_start=73
-  _LOGITSWARPERPARAMETERS._serialized_end=167
-  _REQUEST._serialized_start=169
-  _REQUEST._serialized_end=287
-  _BATCH._serialized_start=289
-  _BATCH._serialized_end=348
-  _BATCHCACHED._serialized_start=350
-  _BATCHCACHED._serialized_end=477
-  _FINISHEDGENERATION._serialized_start=479
-  _FINISHEDGENERATION._serialized_end=527
-  _CACHEENTRY._serialized_start=529
-  _CACHEENTRY._serialized_end=599
-  _RESPONSE._serialized_start=602
-  _RESPONSE._serialized_end=730
-  _EMPTY._serialized_start=732
-  _EMPTY._serialized_end=739
-  _TEXTGENERATION._serialized_start=742
-  _TEXTGENERATION._serialized_end=1018
-# @@protoc_insertion_point(module_scope)
--- a/server/bloom_inference/pb/generate_pb2_grpc.py
+++ b/server/bloom_inference/pb/generate_pb2_grpc.py
@ -1,169 +0,0 @@
-# Generated by the gRPC Python protocol compiler plugin. DO NOT EDIT!
-"""Client and server classes corresponding to protobuf-defined services."""
-import grpc
-
-from . import generate_pb2 as generate__pb2
-
-
-class TextGenerationStub(object):
-    """Missing associated documentation comment in .proto file."""
-
-    def __init__(self, channel):
-        """Constructor.
-
-        Args:
-            channel: A grpc.Channel.
-        """
-        self.ServiceDiscovery = channel.unary_unary(
-                '/generate.v1.TextGeneration/ServiceDiscovery',
-                request_serializer=generate__pb2.Empty.SerializeToString,
-                response_deserializer=generate__pb2.ServiceDiscoveryResponse.FromString,
-                )
-        self.ClearCache = channel.unary_unary(
-                '/generate.v1.TextGeneration/ClearCache',
-                request_serializer=generate__pb2.Empty.SerializeToString,
-                response_deserializer=generate__pb2.Empty.FromString,
-                )
-        self.Generate = channel.unary_unary(
-                '/generate.v1.TextGeneration/Generate',
-                request_serializer=generate__pb2.Batch.SerializeToString,
-                response_deserializer=generate__pb2.Response.FromString,
-                )
-        self.GenerateWithCache = channel.unary_unary(
-                '/generate.v1.TextGeneration/GenerateWithCache',
-                request_serializer=generate__pb2.BatchCached.SerializeToString,
-                response_deserializer=generate__pb2.Response.FromString,
-                )
-
-
-class TextGenerationServicer(object):
-    """Missing associated documentation comment in .proto file."""
-
-    def ServiceDiscovery(self, request, context):
-        """/ Service discovery
-        """
-        context.set_code(grpc.StatusCode.UNIMPLEMENTED)
-        context.set_details('Method not implemented!')
-        raise NotImplementedError('Method not implemented!')
-
-    def ClearCache(self, request, context):
-        """/ Empties batch cache
-        """
-        context.set_code(grpc.StatusCode.UNIMPLEMENTED)
-        context.set_details('Method not implemented!')
-        raise NotImplementedError('Method not implemented!')
-
-    def Generate(self, request, context):
-        """/ Generate tokens for a batch without cache
-        """
-        context.set_code(grpc.StatusCode.UNIMPLEMENTED)
-        context.set_details('Method not implemented!')
-        raise NotImplementedError('Method not implemented!')
-
-    def GenerateWithCache(self, request, context):
-        """/ Generate tokens for a batch with cache
-        """
-        context.set_code(grpc.StatusCode.UNIMPLEMENTED)
-        context.set_details('Method not implemented!')
-        raise NotImplementedError('Method not implemented!')
-
-
-def add_TextGenerationServicer_to_server(servicer, server):
-    rpc_method_handlers = {
-            'ServiceDiscovery': grpc.unary_unary_rpc_method_handler(
-                    servicer.ServiceDiscovery,
-                    request_deserializer=generate__pb2.Empty.FromString,
-                    response_serializer=generate__pb2.ServiceDiscoveryResponse.SerializeToString,
-            ),
-            'ClearCache': grpc.unary_unary_rpc_method_handler(
-                    servicer.ClearCache,
-                    request_deserializer=generate__pb2.Empty.FromString,
-                    response_serializer=generate__pb2.Empty.SerializeToString,
-            ),
-            'Generate': grpc.unary_unary_rpc_method_handler(
-                    servicer.Generate,
-                    request_deserializer=generate__pb2.Batch.FromString,
-                    response_serializer=generate__pb2.Response.SerializeToString,
-            ),
-            'GenerateWithCache': grpc.unary_unary_rpc_method_handler(
-                    servicer.GenerateWithCache,
-                    request_deserializer=generate__pb2.BatchCached.FromString,
-                    response_serializer=generate__pb2.Response.SerializeToString,
-            ),
-    }
-    generic_handler = grpc.method_handlers_generic_handler(
-            'generate.v1.TextGeneration', rpc_method_handlers)
-    server.add_generic_rpc_handlers((generic_handler,))
-
-
- # This class is part of an EXPERIMENTAL API.
-class TextGeneration(object):
-    """Missing associated documentation comment in .proto file."""
-
-    @staticmethod
-    def ServiceDiscovery(request,
-            target,
-            options=(),
-            channel_credentials=None,
-            call_credentials=None,
-            insecure=False,
-            compression=None,
-            wait_for_ready=None,
-            timeout=None,
-            metadata=None):
-        return grpc.experimental.unary_unary(request, target, '/generate.v1.TextGeneration/ServiceDiscovery',
-            generate__pb2.Empty.SerializeToString,
-            generate__pb2.ServiceDiscoveryResponse.FromString,
-            options, channel_credentials,
-            insecure, call_credentials, compression, wait_for_ready, timeout, metadata)
-
-    @staticmethod
-    def ClearCache(request,
-            target,
-            options=(),
-            channel_credentials=None,
-            call_credentials=None,
-            insecure=False,
-            compression=None,
-            wait_for_ready=None,
-            timeout=None,
-            metadata=None):
-        return grpc.experimental.unary_unary(request, target, '/generate.v1.TextGeneration/ClearCache',
-            generate__pb2.Empty.SerializeToString,
-            generate__pb2.Empty.FromString,
-            options, channel_credentials,
-            insecure, call_credentials, compression, wait_for_ready, timeout, metadata)
-
-    @staticmethod
-    def Generate(request,
-            target,
-            options=(),
-            channel_credentials=None,
-            call_credentials=None,
-            insecure=False,
-            compression=None,
-            wait_for_ready=None,
-            timeout=None,
-            metadata=None):
-        return grpc.experimental.unary_unary(request, target, '/generate.v1.TextGeneration/Generate',
-            generate__pb2.Batch.SerializeToString,
-            generate__pb2.Response.FromString,
-            options, channel_credentials,
-            insecure, call_credentials, compression, wait_for_ready, timeout, metadata)
-
-    @staticmethod
-    def GenerateWithCache(request,
-            target,
-            options=(),
-            channel_credentials=None,
-            call_credentials=None,
-            insecure=False,
-            compression=None,
-            wait_for_ready=None,
-            timeout=None,
-            metadata=None):
-        return grpc.experimental.unary_unary(request, target, '/generate.v1.TextGeneration/GenerateWithCache',
-            generate__pb2.BatchCached.SerializeToString,
-            generate__pb2.Response.FromString,
-            options, channel_credentials,
-            insecure, call_credentials, compression, wait_for_ready, timeout, metadata)
--- a/server/bloom_inference/pb/generate_pb2_grpc.py-e
+++ b/server/bloom_inference/pb/generate_pb2_grpc.py-e
@ -1,169 +0,0 @@
-# Generated by the gRPC Python protocol compiler plugin. DO NOT EDIT!
-"""Client and server classes corresponding to protobuf-defined services."""
-import grpc
-
-import generate_pb2 as generate__pb2
-
-
-class TextGenerationStub(object):
-    """Missing associated documentation comment in .proto file."""
-
-    def __init__(self, channel):
-        """Constructor.
-
-        Args:
-            channel: A grpc.Channel.
-        """
-        self.ServiceDiscovery = channel.unary_unary(
-                '/generate.v1.TextGeneration/ServiceDiscovery',
-                request_serializer=generate__pb2.Empty.SerializeToString,
-                response_deserializer=generate__pb2.ServiceDiscoveryResponse.FromString,
-                )
-        self.ClearCache = channel.unary_unary(
-                '/generate.v1.TextGeneration/ClearCache',
-                request_serializer=generate__pb2.Empty.SerializeToString,
-                response_deserializer=generate__pb2.Empty.FromString,
-                )
-        self.Generate = channel.unary_unary(
-                '/generate.v1.TextGeneration/Generate',
-                request_serializer=generate__pb2.Batch.SerializeToString,
-                response_deserializer=generate__pb2.Response.FromString,
-                )
-        self.GenerateWithCache = channel.unary_unary(
-                '/generate.v1.TextGeneration/GenerateWithCache',
-                request_serializer=generate__pb2.BatchCached.SerializeToString,
-                response_deserializer=generate__pb2.Response.FromString,
-                )
-
-
-class TextGenerationServicer(object):
-    """Missing associated documentation comment in .proto file."""
-
-    def ServiceDiscovery(self, request, context):
-        """/ Service discovery
-        """
-        context.set_code(grpc.StatusCode.UNIMPLEMENTED)
-        context.set_details('Method not implemented!')
-        raise NotImplementedError('Method not implemented!')
-
-    def ClearCache(self, request, context):
-        """/ Empties batch cache
-        """
-        context.set_code(grpc.StatusCode.UNIMPLEMENTED)
-        context.set_details('Method not implemented!')
-        raise NotImplementedError('Method not implemented!')
-
-    def Generate(self, request, context):
-        """/ Generate tokens for a batch without cache
-        """
-        context.set_code(grpc.StatusCode.UNIMPLEMENTED)
-        context.set_details('Method not implemented!')
-        raise NotImplementedError('Method not implemented!')
-
-    def GenerateWithCache(self, request, context):
-        """/ Generate tokens for a batch with cache
-        """
-        context.set_code(grpc.StatusCode.UNIMPLEMENTED)
-        context.set_details('Method not implemented!')
-        raise NotImplementedError('Method not implemented!')
-
-
-def add_TextGenerationServicer_to_server(servicer, server):
-    rpc_method_handlers = {
-            'ServiceDiscovery': grpc.unary_unary_rpc_method_handler(
-                    servicer.ServiceDiscovery,
-                    request_deserializer=generate__pb2.Empty.FromString,
-                    response_serializer=generate__pb2.ServiceDiscoveryResponse.SerializeToString,
-            ),
-            'ClearCache': grpc.unary_unary_rpc_method_handler(
-                    servicer.ClearCache,
-                    request_deserializer=generate__pb2.Empty.FromString,
-                    response_serializer=generate__pb2.Empty.SerializeToString,
-            ),
-            'Generate': grpc.unary_unary_rpc_method_handler(
-                    servicer.Generate,
-                    request_deserializer=generate__pb2.Batch.FromString,
-                    response_serializer=generate__pb2.Response.SerializeToString,
-            ),
-            'GenerateWithCache': grpc.unary_unary_rpc_method_handler(
-                    servicer.GenerateWithCache,
-                    request_deserializer=generate__pb2.BatchCached.FromString,
-                    response_serializer=generate__pb2.Response.SerializeToString,
-            ),
-    }
-    generic_handler = grpc.method_handlers_generic_handler(
-            'generate.v1.TextGeneration', rpc_method_handlers)
-    server.add_generic_rpc_handlers((generic_handler,))
-
-
- # This class is part of an EXPERIMENTAL API.
-class TextGeneration(object):
-    """Missing associated documentation comment in .proto file."""
-
-    @staticmethod
-    def ServiceDiscovery(request,
-            target,
-            options=(),
-            channel_credentials=None,
-            call_credentials=None,
-            insecure=False,
-            compression=None,
-            wait_for_ready=None,
-            timeout=None,
-            metadata=None):
-        return grpc.experimental.unary_unary(request, target, '/generate.v1.TextGeneration/ServiceDiscovery',
-            generate__pb2.Empty.SerializeToString,
-            generate__pb2.ServiceDiscoveryResponse.FromString,
-            options, channel_credentials,
-            insecure, call_credentials, compression, wait_for_ready, timeout, metadata)
-
-    @staticmethod
-    def ClearCache(request,
-            target,
-            options=(),
-            channel_credentials=None,
-            call_credentials=None,
-            insecure=False,
-            compression=None,
-            wait_for_ready=None,
-            timeout=None,
-            metadata=None):
-        return grpc.experimental.unary_unary(request, target, '/generate.v1.TextGeneration/ClearCache',
-            generate__pb2.Empty.SerializeToString,
-            generate__pb2.Empty.FromString,
-            options, channel_credentials,
-            insecure, call_credentials, compression, wait_for_ready, timeout, metadata)
-
-    @staticmethod
-    def Generate(request,
-            target,
-            options=(),
-            channel_credentials=None,
-            call_credentials=None,
-            insecure=False,
-            compression=None,
-            wait_for_ready=None,
-            timeout=None,
-            metadata=None):
-        return grpc.experimental.unary_unary(request, target, '/generate.v1.TextGeneration/Generate',
-            generate__pb2.Batch.SerializeToString,
-            generate__pb2.Response.FromString,
-            options, channel_credentials,
-            insecure, call_credentials, compression, wait_for_ready, timeout, metadata)
-
-    @staticmethod
-    def GenerateWithCache(request,
-            target,
-            options=(),
-            channel_credentials=None,
-            call_credentials=None,
-            insecure=False,
-            compression=None,
-            wait_for_ready=None,
-            timeout=None,
-            metadata=None):
-        return grpc.experimental.unary_unary(request, target, '/generate.v1.TextGeneration/GenerateWithCache',
-            generate__pb2.BatchCached.SerializeToString,
-            generate__pb2.Response.FromString,
-            options, channel_credentials,
-            insecure, call_credentials, compression, wait_for_ready, timeout, metadata)