AssessedReplica
One independent model replica in the conservative concurrency plan.
shardingSharding (string)required
shards object[]required
Array [
nodeIdNodeid (string)required
backend objectrequired
anyOf
- string
- null
string
estimatedMemoryBytes objectrequired
Shared estimated footprint; null for runtime-selected RPC partitions.
- integer
- null
integer
usableMemoryBytesUsablememorybytes (integer)required
Memory available after current commitments and working-set caps.
memoryPoolMemorypool (string)required
Possible values: [ram, vram]
]
concurrentRequestsConcurrentrequests (integer)required
contextPoolTokensContextpooltokens (integer)required
Aggregate reserved context for requests assigned to this replica.
existingInstanceId object
anyOf
- string
- null
string
AssessedReplica
{
"sharding": "string",
"shards": [
{
"nodeId": "string",
"backend": "string",
"estimatedMemoryBytes": 0,
"usableMemoryBytes": 0,
"memoryPool": "ram"
}
],
"concurrentRequests": 0,
"contextPoolTokens": 0,
"existingInstanceId": "string"
}