RunnerFlightRecorderEntry
One retained runner flight-recorder entry.
UTC timestamp when the runner emitted the update.
Runner phase at this entry.
Possible values: [created, idle, connect_group, load_model, warmup, task_submission, task_agreement, prompt_build, vision_preprocess, kv_cache_lookup, prefill_barrier, prefill_pipeline, prefill_stream, decode_barrier, decode_wait_first_token, decode_stream, parser, cancel_requested, cancel_observed, completion, error, shutdown_cleanup]
Short event name within the phase.
detail object
Compact human-readable detail for diagnostics.
- string
- null
attrs object
Structured low-cardinality diagnostic attributes.
property name* object
- string
- integer
- number
- boolean
- string[]
context objectrequired
Stable runner identity fields for this entry.
Node ID that owns this runner.
Runner ID.
pid object
Runner subprocess PID.
- integer
- null
Instance ID.
Model assigned to this runner.
Distributed rank for this runner.
Distributed world size.
Inclusive first layer on this shard.
Exclusive final layer on this shard.
Total model layers.
taskId object
Task ID associated with the entry, when known.
- string
- null
commandId object
Command ID associated with the entry, when known.
- string
- null
mlxMemory object
MLX memory snapshot captured with this entry, when present.
- MlxMemorySnapshot
- null
UTC timestamp when the snapshot was taken.
active object
Currently active MLX memory, when the runtime exposes it.
- Memory
- null
0cache object
MLX cache memory, when the runtime exposes it.
- Memory
- null
0peak object
Peak MLX memory since the last reset, when available.
- Memory
- null
0wiredLimit object
Configured MLX wired memory limit when known. Current MLX releases do not expose a getter on all platforms, so this may be null.
- Memory
- null
0Runtime module that supplied the measurement, such as mlx.core.
{
"at": "string",
"phase": "created",
"event": "string",
"detail": "string",
"attrs": {},
"context": {
"nodeId": "string",
"runnerId": "string",
"pid": 0,
"instanceId": "string",
"modelId": "string",
"rank": 0,
"worldSize": 0,
"startLayer": 0,
"endLayer": 0,
"nLayers": 0
},
"taskId": "string",
"commandId": "string",
"mlxMemory": {
"generatedAt": "string",
"active": {
"inBytes": 0
},
"cache": {
"inBytes": 0
},
"peak": {
"inBytes": 0
},
"wiredLimit": {
"inBytes": 0
},
"source": "string"
}
}