Python pickles (.bin, .pt, .pth, .ckpt, .pkl) run whatever they hold when loaded, as the engine's user, on the node; that is how the malicious models found on Hugging Face work. The node refuses such a source, or a mirror set holding one, before fetching anything. A model added with one, or given one, is refused, while one already in the catalog still loads and is refused by its node with the same words. vLLM and SGLang downloading a model by its id get --load-format safetensors. The mirror page marks the file. allow_pickle: true on a model lets it through on purpose, carried to the node in EngineProfile.allow_pickle. BACKLOG M lists the rest: checksums against Hugging Face on every path, its own scan, trusted publishers, engines without the internet, an eval before an untrusted model serves. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
1 parent
6752938e6d
commit
4466d2d15a
31 files changed
+447
-44
No files matched your search
@@ -3790,7 +3790,10 @@ type EngineProfile struct {
|
||||
Adapters []*LoraAdapter `protobuf:"bytes,12,rep,name=adapters,proto3" json:"adapters,omitempty"`
|
||||
// kv_events has a vLLM engine publish its KV cache events to the agent, for
|
||||
// the router's precise index.
|
||||
KvEvents bool `protobuf:"varint,13,opt,name=kv_events,json=kvEvents,proto3" json:"kv_events,omitempty"`
|
||||
KvEvents bool `protobuf:"varint,13,opt,name=kv_events,json=kvEvents,proto3" json:"kv_events,omitempty"`
|
||||
// allow_pickle lets the node fetch weights in a pickle format, which run
|
||||
// code when loaded: the catalog's allow_pickle, set on purpose.
|
||||
AllowPickle bool `protobuf:"varint,14,opt,name=allow_pickle,json=allowPickle,proto3" json:"allow_pickle,omitempty"`
|
||||
unknownFields protoimpl.UnknownFields
|
||||
sizeCache protoimpl.SizeCache
|
||||
}
|
||||
@@ -3916,6 +3919,13 @@ func (x *EngineProfile) GetKvEvents() bool {
|
||||
return false
|
||||
}
|
||||
|
||||
func (x *EngineProfile) GetAllowPickle() bool {
|
||||
if x != nil {
|
||||
return x.AllowPickle
|
||||
}
|
||||
return false
|
||||
}
|
||||
|
||||
// RemoveWeights deletes cached model files a node no longer needs.
|
||||
//
|
||||
// The paths are computed by the control plane from the catalog, but the agent
|
||||
@@ -5462,7 +5472,7 @@ 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\"\xcd\x03\n" +
|
||||
"cpuThreads\"\xf0\x03\n" +
|
||||
"\rEngineProfile\x12\x12\n" +
|
||||
"\x04name\x18\x01 \x01(\tR\x04name\x12\x16\n" +
|
||||
"\x06engine\x18\x02 \x01(\tR\x06engine\x12\x1b\n" +
|
||||
@@ -5478,7 +5488,8 @@ const file_llmgw_v1_agent_proto_rawDesc = "" +
|
||||
" \x01(\tR\tmodelPath\x12*\n" +
|
||||
"\x11served_model_name\x18\v \x01(\tR\x0fservedModelName\x121\n" +
|
||||
"\badapters\x18\f \x03(\v2\x15.llmgw.v1.LoraAdapterR\badapters\x12\x1b\n" +
|
||||
"\tkv_events\x18\r \x01(\bR\bkvEvents\x1a6\n" +
|
||||
"\tkv_events\x18\r \x01(\bR\bkvEvents\x12!\n" +
|
||||
"\fallow_pickle\x18\x0e \x01(\bR\vallowPickle\x1a6\n" +
|
||||
"\bEnvEntry\x12\x10\n" +
|
||||
"\x03key\x18\x01 \x01(\tR\x03key\x12\x14\n" +
|
||||
"\x05value\x18\x02 \x01(\tR\x05value:\x028\x01\"%\n" +
|
||||
|
||||
@@ -749,6 +749,9 @@ message EngineProfile {
|
||||
// kv_events has a vLLM engine publish its KV cache events to the agent, for
|
||||
// the router's precise index.
|
||||
bool kv_events = 13;
|
||||
// allow_pickle lets the node fetch weights in a pickle format, which run
|
||||
// code when loaded: the catalog's allow_pickle, set on purpose.
|
||||
bool allow_pickle = 14;
|
||||
}
|
||||
|
||||
// RemoveWeights deletes cached model files a node no longer needs.
|
||||
|
||||
Reference in new issue
Block a user