Serve LoRA adapters on llama.cpp models, asked for by name
Release / build (push) Successful in 1m11s
Release / notes (push) Successful in 3s
CI / test (push) Successful in 3m47s

A model's adapters are fetched by each node with its weights and loaded
unapplied at start; a request naming an adapter reaches the model's
replicas with llama.cpp's per-request lora field. Adapter names share the
model namespace, are listed, and follow allowlists on their own. The
router's config seed and pushed catalog now build the name map in one place.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
This commit is contained in:
Ilker ManapandClaude Opus 5.5 committed 2026-09-30 23:40:47 +02:00
1 parent 94eec557ad
commit cf53904cc5
18 files changed
+542 -41

No files matched your search

+96 -26
View File
@@ -2873,8 +2873,11 @@ type EngineProfile struct {
Env map[string]string `protobuf:"bytes,9,rep,name=env,proto3" json:"env,omitempty" protobuf_key:"bytes,1,opt,name=key" protobuf_val:"bytes,2,opt,name=value"`
ModelPath string `protobuf:"bytes,10,opt,name=model_path,json=modelPath,proto3" json:"model_path,omitempty"`
ServedModelName string `protobuf:"bytes,11,opt,name=served_model_name,json=servedModelName,proto3" json:"served_model_name,omitempty"`
unknownFields protoimpl.UnknownFields
sizeCache protoimpl.SizeCache
// adapters are LoRA adapters loaded beside the model, in order: the index
// is the id a request applies one by.
Adapters []*LoraAdapter `protobuf:"bytes,12,rep,name=adapters,proto3" json:"adapters,omitempty"`
unknownFields protoimpl.UnknownFields
sizeCache protoimpl.SizeCache
}
func (x *EngineProfile) Reset() {
@@ -2984,6 +2987,13 @@ func (x *EngineProfile) GetServedModelName() string {
return ""
}
func (x *EngineProfile) GetAdapters() []*LoraAdapter {
if x != nil {
return x.Adapters
}
return nil
}
// RemoveWeights deletes cached model files a node no longer needs.
//
// The paths are computed by the control plane from the catalog, but the agent
@@ -3777,6 +3787,60 @@ func (x *UpgradeReply) GetError() string {
return ""
}
// LoraAdapter is one adapter: the name clients ask for it by, and its source,
// which the agent fetches as it does the model's weights.
type LoraAdapter struct {
state protoimpl.MessageState `protogen:"open.v1"`
Name string `protobuf:"bytes,1,opt,name=name,proto3" json:"name,omitempty"`
Source string `protobuf:"bytes,2,opt,name=source,proto3" json:"source,omitempty"`
unknownFields protoimpl.UnknownFields
sizeCache protoimpl.SizeCache
}
func (x *LoraAdapter) Reset() {
*x = LoraAdapter{}
mi := &file_llmgw_v1_agent_proto_msgTypes[36]
ms := protoimpl.X.MessageStateOf(protoimpl.Pointer(x))
ms.StoreMessageInfo(mi)
}
func (x *LoraAdapter) String() string {
return protoimpl.X.MessageStringOf(x)
}
func (*LoraAdapter) ProtoMessage() {}
func (x *LoraAdapter) ProtoReflect() protoreflect.Message {
mi := &file_llmgw_v1_agent_proto_msgTypes[36]
if x != nil {
ms := protoimpl.X.MessageStateOf(protoimpl.Pointer(x))
if ms.LoadMessageInfo() == nil {
ms.StoreMessageInfo(mi)
}
return ms
}
return mi.MessageOf(x)
}
// Deprecated: Use LoraAdapter.ProtoReflect.Descriptor instead.
func (*LoraAdapter) Descriptor() ([]byte, []int) {
return file_llmgw_v1_agent_proto_rawDescGZIP(), []int{36}
}
func (x *LoraAdapter) GetName() string {
if x != nil {
return x.Name
}
return ""
}
func (x *LoraAdapter) GetSource() string {
if x != nil {
return x.Source
}
return ""
}
var File_llmgw_v1_agent_proto protoreflect.FileDescriptor
const file_llmgw_v1_agent_proto_rawDesc = "" +
@@ -4066,7 +4130,7 @@ const file_llmgw_v1_agent_proto_rawDesc = "" +
"profile_fp\x18\x0f \x01(\tR\tprofileFp\x12\x17\n" +
"\aapi_key\x18\x10 \x01(\tR\x06apiKey\x12\x1f\n" +
"\vcpu_threads\x18\x11 \x01(\x05R\n" +
"cpuThreads\"\xfd\x02\n" +
"cpuThreads\"\xb0\x03\n" +
"\rEngineProfile\x12\x12\n" +
"\x04name\x18\x01 \x01(\tR\x04name\x12\x16\n" +
"\x06engine\x18\x02 \x01(\tR\x06engine\x12\x1b\n" +
@@ -4080,7 +4144,8 @@ const file_llmgw_v1_agent_proto_rawDesc = "" +
"\n" +
"model_path\x18\n" +
" \x01(\tR\tmodelPath\x12*\n" +
"\x11served_model_name\x18\v \x01(\tR\x0fservedModelName\x1a6\n" +
"\x11served_model_name\x18\v \x01(\tR\x0fservedModelName\x121\n" +
"\badapters\x18\f \x03(\v2\x15.llmgw.v1.LoraAdapterR\badapters\x1a6\n" +
"\bEnvEntry\x12\x10\n" +
"\x03key\x18\x01 \x01(\tR\x03key\x12\x14\n" +
"\x05value\x18\x02 \x01(\tR\x05value:\x028\x01\"%\n" +
@@ -4143,7 +4208,10 @@ const file_llmgw_v1_agent_proto_rawDesc = "" +
"\n" +
"request_id\x18\x01 \x01(\tR\trequestId\x12\x18\n" +
"\aversion\x18\x02 \x01(\tR\aversion\x12\x14\n" +
"\x05error\x18\x03 \x01(\tR\x05error2O\n" +
"\x05error\x18\x03 \x01(\tR\x05error\"9\n" +
"\vLoraAdapter\x12\x12\n" +
"\x04name\x18\x01 \x01(\tR\x04name\x12\x16\n" +
"\x06source\x18\x02 \x01(\tR\x06source2O\n" +
"\fAgentService\x12?\n" +
"\aConnect\x12\x16.llmgw.v1.AgentMessage\x1a\x18.llmgw.v1.ControlMessage(\x010\x01B\x93\x01\n" +
"\fcom.llmgw.v1B\n" +
@@ -4162,7 +4230,7 @@ func file_llmgw_v1_agent_proto_rawDescGZIP() []byte {
}
var file_llmgw_v1_agent_proto_enumTypes = make([]protoimpl.EnumInfo, 1)
var file_llmgw_v1_agent_proto_msgTypes = make([]protoimpl.MessageInfo, 42)
var file_llmgw_v1_agent_proto_msgTypes = make([]protoimpl.MessageInfo, 43)
var file_llmgw_v1_agent_proto_goTypes = []any{
(ShardStatus_State)(0), // 0: llmgw.v1.ShardStatus.State
(*AgentMessage)(nil), // 1: llmgw.v1.AgentMessage
@@ -4201,12 +4269,13 @@ var file_llmgw_v1_agent_proto_goTypes = []any{
(*FabricTestReply)(nil), // 34: llmgw.v1.FabricTestReply
(*UpgradeAgent)(nil), // 35: llmgw.v1.UpgradeAgent
(*UpgradeReply)(nil), // 36: llmgw.v1.UpgradeReply
nil, // 37: llmgw.v1.Register.LabelsEntry
nil, // 38: llmgw.v1.Register.EngineVersionsEntry
nil, // 39: llmgw.v1.GPU.NicPathsEntry
nil, // 40: llmgw.v1.IBPort.CountersEntry
nil, // 41: llmgw.v1.Heartbeat.EngineVersionsEntry
nil, // 42: llmgw.v1.EngineProfile.EnvEntry
(*LoraAdapter)(nil), // 37: llmgw.v1.LoraAdapter
nil, // 38: llmgw.v1.Register.LabelsEntry
nil, // 39: llmgw.v1.Register.EngineVersionsEntry
nil, // 40: llmgw.v1.GPU.NicPathsEntry
nil, // 41: llmgw.v1.IBPort.CountersEntry
nil, // 42: llmgw.v1.Heartbeat.EngineVersionsEntry
nil, // 43: llmgw.v1.EngineProfile.EnvEntry
}
var file_llmgw_v1_agent_proto_depIdxs = []int32{
3, // 0: llmgw.v1.AgentMessage.register:type_name -> llmgw.v1.Register
@@ -4226,24 +4295,24 @@ var file_llmgw_v1_agent_proto_depIdxs = []int32{
31, // 14: llmgw.v1.ControlMessage.fabric_scan:type_name -> llmgw.v1.FabricScanRequest
33, // 15: llmgw.v1.ControlMessage.fabric_test:type_name -> llmgw.v1.FabricTestRequest
35, // 16: llmgw.v1.ControlMessage.upgrade:type_name -> llmgw.v1.UpgradeAgent
37, // 17: llmgw.v1.Register.labels:type_name -> llmgw.v1.Register.LabelsEntry
38, // 17: llmgw.v1.Register.labels:type_name -> llmgw.v1.Register.LabelsEntry
7, // 18: llmgw.v1.Register.gpus:type_name -> llmgw.v1.GPU
8, // 19: llmgw.v1.Register.fabrics:type_name -> llmgw.v1.FabricAttachment
38, // 20: llmgw.v1.Register.engine_versions:type_name -> llmgw.v1.Register.EngineVersionsEntry
39, // 20: llmgw.v1.Register.engine_versions:type_name -> llmgw.v1.Register.EngineVersionsEntry
6, // 21: llmgw.v1.Register.running_shards:type_name -> llmgw.v1.RunningShard
9, // 22: llmgw.v1.Register.weights:type_name -> llmgw.v1.LocalWeights
5, // 23: llmgw.v1.Register.storage:type_name -> llmgw.v1.Storage
4, // 24: llmgw.v1.Register.host:type_name -> llmgw.v1.Host
15, // 25: llmgw.v1.Register.imex:type_name -> llmgw.v1.IMEX
0, // 26: llmgw.v1.RunningShard.state:type_name -> llmgw.v1.ShardStatus.State
39, // 27: llmgw.v1.GPU.nic_paths:type_name -> llmgw.v1.GPU.NicPathsEntry
40, // 27: llmgw.v1.GPU.nic_paths:type_name -> llmgw.v1.GPU.NicPathsEntry
12, // 28: llmgw.v1.NodeLoad.shards:type_name -> llmgw.v1.ShardLoad
11, // 29: llmgw.v1.NodeLoad.gpus:type_name -> llmgw.v1.GPUSensor
40, // 30: llmgw.v1.IBPort.counters:type_name -> llmgw.v1.IBPort.CountersEntry
41, // 30: llmgw.v1.IBPort.counters:type_name -> llmgw.v1.IBPort.CountersEntry
14, // 31: llmgw.v1.IBPort.subnet_managers:type_name -> llmgw.v1.SubnetManager
5, // 32: llmgw.v1.Heartbeat.storage:type_name -> llmgw.v1.Storage
9, // 33: llmgw.v1.Heartbeat.weights:type_name -> llmgw.v1.LocalWeights
41, // 34: llmgw.v1.Heartbeat.engine_versions:type_name -> llmgw.v1.Heartbeat.EngineVersionsEntry
42, // 34: llmgw.v1.Heartbeat.engine_versions:type_name -> llmgw.v1.Heartbeat.EngineVersionsEntry
20, // 35: llmgw.v1.Heartbeat.provision:type_name -> llmgw.v1.ProvisionStatus
10, // 36: llmgw.v1.Heartbeat.load:type_name -> llmgw.v1.NodeLoad
13, // 37: llmgw.v1.Heartbeat.ib_ports:type_name -> llmgw.v1.IBPort
@@ -4254,14 +4323,15 @@ var file_llmgw_v1_agent_proto_depIdxs = []int32{
0, // 42: llmgw.v1.ShardStatus.state:type_name -> llmgw.v1.ShardStatus.State
22, // 43: llmgw.v1.ShardStatus.fetch:type_name -> llmgw.v1.FetchProgress
24, // 44: llmgw.v1.StartShard.profile:type_name -> llmgw.v1.EngineProfile
42, // 45: llmgw.v1.EngineProfile.env:type_name -> llmgw.v1.EngineProfile.EnvEntry
1, // 46: llmgw.v1.AgentService.Connect:input_type -> llmgw.v1.AgentMessage
2, // 47: llmgw.v1.AgentService.Connect:output_type -> llmgw.v1.ControlMessage
47, // [47:48] is the sub-list for method output_type
46, // [46:47] is the sub-list for method input_type
46, // [46:46] is the sub-list for extension type_name
46, // [46:46] is the sub-list for extension extendee
0, // [0:46] is the sub-list for field type_name
43, // 45: llmgw.v1.EngineProfile.env:type_name -> llmgw.v1.EngineProfile.EnvEntry
37, // 46: llmgw.v1.EngineProfile.adapters:type_name -> llmgw.v1.LoraAdapter
1, // 47: llmgw.v1.AgentService.Connect:input_type -> llmgw.v1.AgentMessage
2, // 48: llmgw.v1.AgentService.Connect:output_type -> llmgw.v1.ControlMessage
48, // [48:49] is the sub-list for method output_type
47, // [47:48] is the sub-list for method input_type
47, // [47:47] is the sub-list for extension type_name
47, // [47:47] is the sub-list for extension extendee
0, // [0:47] is the sub-list for field type_name
}
func init() { file_llmgw_v1_agent_proto_init() }
@@ -4296,7 +4366,7 @@ func file_llmgw_v1_agent_proto_init() {
GoPackagePath: reflect.TypeOf(x{}).PkgPath(),
RawDescriptor: unsafe.Slice(unsafe.StringData(file_llmgw_v1_agent_proto_rawDesc), len(file_llmgw_v1_agent_proto_rawDesc)),
NumEnums: 1,
NumMessages: 42,
NumMessages: 43,
NumExtensions: 0,
NumServices: 1,
},
+10
View File
@@ -572,6 +572,9 @@ message EngineProfile {
map<string, string> env = 9;
string model_path = 10;
string served_model_name = 11;
// adapters are LoRA adapters loaded beside the model, in order: the index
// is the id a request applies one by.
repeated LoraAdapter adapters = 12;
}
// RemoveWeights deletes cached model files a node no longer needs.
@@ -704,3 +707,10 @@ message UpgradeReply {
string version = 2;
string error = 3;
}
// LoraAdapter is one adapter: the name clients ask for it by, and its source,
// which the agent fetches as it does the model's weights.
message LoraAdapter {
string name = 1;
string source = 2;
}