You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@beam.apache.org by da...@apache.org on 2022/09/30 15:17:19 UTC
[beam] branch master updated: RunInference Benchmarks UI (#23426)
This is an automated email from the ASF dual-hosted git repository.
damccorm pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/beam.git
The following commit(s) were added to refs/heads/master by this push:
new f2d426d2d2c RunInference Benchmarks UI (#23426)
f2d426d2d2c is described below
commit f2d426d2d2c088a573ab5a96e6e6bfc1bbf45b21
Author: Anand Inguva <34...@users.noreply.github.com>
AuthorDate: Fri Sep 30 11:17:11 2022 -0400
RunInference Benchmarks UI (#23426)
* Add additional plots for 2 more metrics
* Change the alias to distinguish among graphs
* Change Yaxes for mean_inference_request_batch_size_*
* Change axis measure unit from seconds to appropriate unit
* Add metrics dashboard for Language Modeling Bert
---
.../Python_ML_RunInference_Benchmark_Tests.json | 940 ++++++++++++++++++++-
1 file changed, 919 insertions(+), 21 deletions(-)
diff --git a/.test-infra/metrics/grafana/dashboards/perftests_metrics/Python_ML_RunInference_Benchmark_Tests.json b/.test-infra/metrics/grafana/dashboards/perftests_metrics/Python_ML_RunInference_Benchmark_Tests.json
index 1e449b04b5b..836227b3081 100644
--- a/.test-infra/metrics/grafana/dashboards/perftests_metrics/Python_ML_RunInference_Benchmark_Tests.json
+++ b/.test-infra/metrics/grafana/dashboards/perftests_metrics/Python_ML_RunInference_Benchmark_Tests.json
@@ -8,32 +8,720 @@
"hide": true,
"iconColor": "rgba(0, 211, 255, 1)",
"name": "Annotations & Alerts",
+ "target": {
+ "limit": 100,
+ "matchAny": false,
+ "tags": [],
+ "type": "dashboard"
+ },
"type": "dashboard"
}
- ]
- },
- "editable": true,
- "gnetId": null,
- "graphTooltip": 0,
- "id": 16,
- "links": [],
- "panels": [
+ ]
+ },
+ "editable": true,
+ "gnetId": null,
+ "graphTooltip": 0,
+ "links": [],
+ "panels": [
+ {
+ "aliasColors": {},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "BeamInfluxDB",
+ "fieldConfig": {
+ "defaults": {
+ "links": []
+ },
+ "overrides": []
+ },
+ "fill": 1,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 9,
+ "w": 12,
+ "x": 0,
+ "y": 0
+ },
+ "hiddenSeries": false,
+ "id": 4,
+ "interval": "24h",
+ "legend": {
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "show": true,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 2,
+ "nullPointMode": "connected",
+ "options": {
+ "alertThreshold": true
+ },
+ "percentage": false,
+ "pluginVersion": "8.1.8",
+ "pointradius": 2,
+ "points": true,
+ "renderer": "flot",
+ "seriesOverrides": [],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "alias": "mean_inference_request_batch_size_resnet101",
+ "groupBy": [
+ {
+ "params": [
+ "$__interval"
+ ],
+ "type": "time"
+ },
+ {
+ "params": [
+ "null"
+ ],
+ "type": "fill"
+ }
+ ],
+ "orderByTime": "ASC",
+ "policy": "default",
+ "query": "SELECT mean(\"value\") FROM \"torch_inference_imagenet_resnet101\" WHERE metric = 'BeamML_PyTorch_pytorchruninference/beamml_runinference_mean_inference_request_batch_size' AND $timeFilter GROUP BY time($__interval), \"metric\"",
+ "rawQuery": true,
+ "refId": "A",
+ "resultFormat": "time_series",
+ "select": [
+ [
+ {
+ "params": [
+ "value"
+ ],
+ "type": "field"
+ },
+ {
+ "params": [],
+ "type": "mean"
+ }
+ ]
+ ],
+ "tags": []
+ },
+ {
+ "alias": "mean_inference_request_batch_size_resnet152",
+ "groupBy": [
+ {
+ "params": [
+ "$__interval"
+ ],
+ "type": "time"
+ },
+ {
+ "params": [
+ "null"
+ ],
+ "type": "fill"
+ }
+ ],
+ "orderByTime": "ASC",
+ "policy": "default",
+ "query": "SELECT mean(\"value\") FROM \"torch_inference_imagenet_resnet152\" WHERE metric = 'BeamML_PyTorch_pytorchruninference/beamml_runinference_mean_inference_request_batch_size' AND $timeFilter GROUP BY time($__interval), \"metric\"",
+ "rawQuery": true,
+ "refId": "B",
+ "resultFormat": "time_series",
+ "select": [
+ [
+ {
+ "params": [
+ "value"
+ ],
+ "type": "field"
+ },
+ {
+ "params": [],
+ "type": "mean"
+ }
+ ]
+ ],
+ "tags": []
+ }
+ ],
+ "thresholds": [],
+ "timeFrom": null,
+ "timeRegions": [],
+ "timeShift": null,
+ "title": "Pytorch RunInference Image Classification 50K - Mean Inference Requested Batch Size",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "transparent": true,
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "$$hashKey": "object:168",
+ "format": "none",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
+ },
+ {
+ "$$hashKey": "object:169",
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
+ }
+ ],
+ "yaxis": {
+ "align": false,
+ "alignLevel": null
+ }
+ },
+ {
+ "aliasColors": {},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "BeamInfluxDB",
+ "fieldConfig": {
+ "defaults": {
+ "links": []
+ },
+ "overrides": []
+ },
+ "fill": 1,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 9,
+ "w": 12,
+ "x": 12,
+ "y": 0
+ },
+ "hiddenSeries": false,
+ "id": 5,
+ "interval": "24h",
+ "legend": {
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "show": true,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 2,
+ "nullPointMode": "connected",
+ "options": {
+ "alertThreshold": true
+ },
+ "percentage": false,
+ "pluginVersion": "8.1.8",
+ "pointradius": 2,
+ "points": true,
+ "renderer": "flot",
+ "seriesOverrides": [],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "alias": "mean_inference_request_batch_size_bert_base_uncased",
+ "groupBy": [
+ {
+ "params": [
+ "$__interval"
+ ],
+ "type": "time"
+ },
+ {
+ "params": [
+ "null"
+ ],
+ "type": "fill"
+ }
+ ],
+ "orderByTime": "ASC",
+ "policy": "default",
+ "query": "SELECT mean(\"value\") FROM \"torch_language_modeling_bert_base_uncased\" WHERE metric = 'BeamML_PyTorch_pytorchruninference/beamml_runinference_mean_inference_request_batch_size' AND $timeFilter GROUP BY time($__interval), \"metric\"",
+ "rawQuery": true,
+ "refId": "A",
+ "resultFormat": "time_series",
+ "select": [
+ [
+ {
+ "params": [
+ "value"
+ ],
+ "type": "field"
+ },
+ {
+ "params": [],
+ "type": "mean"
+ }
+ ]
+ ],
+ "tags": []
+ },
+ {
+ "alias": "mean_inference_request_batch_size_bert_large_uncased",
+ "groupBy": [
+ {
+ "params": [
+ "$__interval"
+ ],
+ "type": "time"
+ },
+ {
+ "params": [
+ "null"
+ ],
+ "type": "fill"
+ }
+ ],
+ "orderByTime": "ASC",
+ "policy": "default",
+ "query": "SELECT mean(\"value\") FROM \"torch_language_modeling_bert_large_uncased\" WHERE metric = 'BeamML_PyTorch_pytorchruninference/beamml_runinference_mean_inference_request_batch_size' AND $timeFilter GROUP BY time($__interval), \"metric\"",
+ "rawQuery": true,
+ "refId": "B",
+ "resultFormat": "time_series",
+ "select": [
+ [
+ {
+ "params": [
+ "value"
+ ],
+ "type": "field"
+ },
+ {
+ "params": [],
+ "type": "mean"
+ }
+ ]
+ ],
+ "tags": []
+ }
+ ],
+ "thresholds": [],
+ "timeFrom": null,
+ "timeRegions": [],
+ "timeShift": null,
+ "title": "Pytorch RunInference Language Modeling using Bert from HuggingFace - Mean Inference Requested Batch Size",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "transparent": true,
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "$$hashKey": "object:168",
+ "format": "none",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
+ },
+ {
+ "$$hashKey": "object:169",
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
+ }
+ ],
+ "yaxis": {
+ "align": false,
+ "alignLevel": null
+ }
+ },
+ {
+ "aliasColors": {},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "BeamInfluxDB",
+ "description": "",
+ "fieldConfig": {
+ "defaults": {
+ "links": []
+ },
+ "overrides": []
+ },
+ "fill": 1,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 9,
+ "w": 12,
+ "x": 0,
+ "y": 9
+ },
+ "hiddenSeries": false,
+ "id": 2,
+ "interval": "24h",
+ "legend": {
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "show": true,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 2,
+ "nullPointMode": "connected",
+ "options": {
+ "alertThreshold": true
+ },
+ "percentage": false,
+ "pluginVersion": "8.1.8",
+ "pointradius": 2,
+ "points": true,
+ "renderer": "flot",
+ "seriesOverrides": [],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "alias": "mean_load_model_latency_milli_seconds_resnet101",
+ "groupBy": [
+ {
+ "params": [
+ "$__interval"
+ ],
+ "type": "time"
+ },
+ {
+ "params": [
+ "null"
+ ],
+ "type": "fill"
+ }
+ ],
+ "orderByTime": "ASC",
+ "policy": "default",
+ "query": "SELECT mean(\"value\") FROM \"torch_inference_imagenet_resnet101\" WHERE metric = 'BeamML_PyTorch_pytorchruninference/beamml_runinference_mean_inference_batch_latency_micro_secs' AND $timeFilter GROUP BY time($__interval), \"metric\"",
+ "rawQuery": true,
+ "refId": "A",
+ "resultFormat": "time_series",
+ "select": [
+ [
+ {
+ "params": [
+ "value"
+ ],
+ "type": "field"
+ },
+ {
+ "params": [],
+ "type": "mean"
+ }
+ ]
+ ],
+ "tags": []
+ },
+ {
+ "alias": "mean_load_model_latency_milli_seconds_resnet_152",
+ "groupBy": [
+ {
+ "params": [
+ "$__interval"
+ ],
+ "type": "time"
+ },
+ {
+ "params": [
+ "null"
+ ],
+ "type": "fill"
+ }
+ ],
+ "orderByTime": "ASC",
+ "policy": "default",
+ "query": "SELECT mean(\"value\") FROM \"torch_inference_imagenet_resnet152\" WHERE metric = 'BeamML_PyTorch_pytorchruninference/beamml_runinference_mean_inference_batch_latency_micro_secs' AND $timeFilter GROUP BY time($__interval), \"metric\"",
+ "rawQuery": true,
+ "refId": "B",
+ "resultFormat": "time_series",
+ "select": [
+ [
+ {
+ "params": [
+ "value"
+ ],
+ "type": "field"
+ },
+ {
+ "params": [],
+ "type": "mean"
+ }
+ ]
+ ],
+ "tags": []
+ }
+ ],
+ "thresholds": [],
+ "timeFrom": null,
+ "timeRegions": [],
+ "timeShift": null,
+ "title": "Pytorch RunInference Image Classification 50K - Mean Inference Batch Latency",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "transparent": true,
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "$$hashKey": "object:72",
+ "format": "µs",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
+ },
+ {
+ "$$hashKey": "object:73",
+ "format": "µs",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
+ }
+ ],
+ "yaxis": {
+ "align": false,
+ "alignLevel": null
+ }
+ },
+ {
+ "aliasColors": {},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "BeamInfluxDB",
+ "fieldConfig": {
+ "defaults": {
+ "links": []
+ },
+ "overrides": []
+ },
+ "fill": 1,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 9,
+ "w": 12,
+ "x": 12,
+ "y": 9
+ },
+ "hiddenSeries": false,
+ "id": 6,
+ "interval": "24h",
+ "legend": {
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "show": true,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 2,
+ "nullPointMode": "connected",
+ "options": {
+ "alertThreshold": true
+ },
+ "percentage": false,
+ "pluginVersion": "8.1.8",
+ "pointradius": 2,
+ "points": true,
+ "renderer": "flot",
+ "seriesOverrides": [],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "alias": "$mean_inference_batch_latency_bert_base_uncased",
+ "groupBy": [
+ {
+ "params": [
+ "$__interval"
+ ],
+ "type": "time"
+ },
+ {
+ "params": [
+ "null"
+ ],
+ "type": "fill"
+ }
+ ],
+ "orderByTime": "ASC",
+ "policy": "default",
+ "query": "SELECT mean(\"value\") FROM \"torch_language_modeling_bert_base_uncased\" WHERE metric = 'BeamML_PyTorch_pytorchruninference/beamml_runinference_mean_inference_batch_latency_micro_secs' AND $timeFilter GROUP BY time($__interval), \"metric\"",
+ "rawQuery": true,
+ "refId": "A",
+ "resultFormat": "time_series",
+ "select": [
+ [
+ {
+ "params": [
+ "value"
+ ],
+ "type": "field"
+ },
+ {
+ "params": [],
+ "type": "mean"
+ }
+ ]
+ ],
+ "tags": []
+ },
+ {
+ "alias": "mean_inference_batch_latency_bert_large_uncased",
+ "groupBy": [
+ {
+ "params": [
+ "$__interval"
+ ],
+ "type": "time"
+ },
+ {
+ "params": [
+ "null"
+ ],
+ "type": "fill"
+ }
+ ],
+ "orderByTime": "ASC",
+ "policy": "default",
+ "query": "SELECT mean(\"value\") FROM \"torch_language_modeling_bert_large_uncased\" WHERE metric = 'BeamML_PyTorch_pytorchruninference/beamml_runinference_mean_inference_batch_latency_micro_secs' AND $timeFilter GROUP BY time($__interval), \"metric\"",
+ "rawQuery": true,
+ "refId": "B",
+ "resultFormat": "time_series",
+ "select": [
+ [
+ {
+ "params": [
+ "value"
+ ],
+ "type": "field"
+ },
+ {
+ "params": [],
+ "type": "mean"
+ }
+ ]
+ ],
+ "tags": []
+ }
+ ],
+ "thresholds": [],
+ "timeFrom": null,
+ "timeRegions": [],
+ "timeShift": null,
+ "title": "Pytorch RunInference Language Modeling using Bert From HuggingFace - Mean Inference Batch Latency",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "transparent": true,
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "$$hashKey": "object:156",
+ "format": "µs",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
+ },
+ {
+ "$$hashKey": "object:157",
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
+ }
+ ],
+ "yaxis": {
+ "align": false,
+ "alignLevel": null
+ }
+ },
{
"aliasColors": {},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "BeamInfluxDB",
+ "fieldConfig": {
+ "defaults": {
+ "links": []
+ },
+ "overrides": []
+ },
"fill": 1,
"fillGradient": 0,
"gridPos": {
"h": 9,
"w": 12,
- "x": 12,
- "y": 0
+ "x": 0,
+ "y": 18
},
"hiddenSeries": false,
- "id": 3,
+ "id": 7,
"interval": "24h",
"legend": {
"avg": false,
@@ -48,9 +736,10 @@
"linewidth": 2,
"nullPointMode": "connected",
"options": {
- "dataLinks": []
+ "alertThreshold": true
},
"percentage": false,
+ "pluginVersion": "8.1.8",
"pointradius": 2,
"points": true,
"renderer": "flot",
@@ -60,7 +749,7 @@
"steppedLine": false,
"targets": [
{
- "alias": "mean_load_model_latency_milli_seconds",
+ "alias": "mean_load_model_latency_milli_seconds_resnet101",
"groupBy": [
{
"params": [
@@ -96,13 +785,220 @@
]
],
"tags": []
+ },
+ {
+ "alias": "mean_load_model_latency_milli_seconds_resnet_152",
+ "groupBy": [
+ {
+ "params": [
+ "$__interval"
+ ],
+ "type": "time"
+ },
+ {
+ "params": [
+ "null"
+ ],
+ "type": "fill"
+ }
+ ],
+ "orderByTime": "ASC",
+ "policy": "default",
+ "query": "SELECT mean(\"value\") FROM \"torch_inference_imagenet_resnet152\" WHERE metric = 'BeamML_PyTorch_pytorchruninference/beamml_runinference_mean_load_model_latency_milli_secs' AND $timeFilter GROUP BY time($__interval), \"metric\"",
+ "rawQuery": true,
+ "refId": "B",
+ "resultFormat": "time_series",
+ "select": [
+ [
+ {
+ "params": [
+ "value"
+ ],
+ "type": "field"
+ },
+ {
+ "params": [],
+ "type": "mean"
+ }
+ ]
+ ],
+ "tags": []
+ }
+ ],
+ "thresholds": [],
+ "timeFrom": null,
+ "timeRegions": [],
+ "timeShift": null,
+ "title": "Pytorch RunInference Image Classification 50K - Mean Load Model Latency",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "transparent": true,
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "$$hashKey": "object:72",
+ "format": "ms",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
+ },
+ {
+ "$$hashKey": "object:73",
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
+ }
+ ],
+ "yaxis": {
+ "align": false,
+ "alignLevel": null
+ }
+ },
+ {
+ "aliasColors": {},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "BeamInfluxDB",
+ "fieldConfig": {
+ "defaults": {
+ "links": []
+ },
+ "overrides": []
+ },
+ "fill": 1,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 9,
+ "w": 12,
+ "x": 12,
+ "y": 18
+ },
+ "hiddenSeries": false,
+ "id": 8,
+ "interval": "24h",
+ "legend": {
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "show": true,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 2,
+ "nullPointMode": "connected",
+ "options": {
+ "alertThreshold": true
+ },
+ "percentage": false,
+ "pluginVersion": "8.1.8",
+ "pointradius": 2,
+ "points": true,
+ "renderer": "flot",
+ "seriesOverrides": [],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "alias": "mean_load_model_latency_milli_seconds_bert_base_uncased",
+ "groupBy": [
+ {
+ "params": [
+ "$__interval"
+ ],
+ "type": "time"
+ },
+ {
+ "params": [
+ "null"
+ ],
+ "type": "fill"
+ }
+ ],
+ "orderByTime": "ASC",
+ "policy": "default",
+ "query": "SELECT mean(\"value\") FROM \"torch_language_modeling_bert_base_uncased\" WHERE metric = 'BeamML_PyTorch_pytorchruninference/beamml_runinference_mean_load_model_latency_milli_secs' AND $timeFilter GROUP BY time($__interval), \"metric\"",
+ "rawQuery": true,
+ "refId": "A",
+ "resultFormat": "time_series",
+ "select": [
+ [
+ {
+ "params": [
+ "value"
+ ],
+ "type": "field"
+ },
+ {
+ "params": [],
+ "type": "mean"
+ }
+ ]
+ ],
+ "tags": []
+ },
+ {
+ "alias": "mean_load_model_latency_milli_seconds_bert_large_uncased",
+ "groupBy": [
+ {
+ "params": [
+ "$__interval"
+ ],
+ "type": "time"
+ },
+ {
+ "params": [
+ "null"
+ ],
+ "type": "fill"
+ }
+ ],
+ "orderByTime": "ASC",
+ "policy": "default",
+ "query": "SELECT mean(\"value\") FROM \"torch_language_modeling_bert_large_uncased\" WHERE metric = 'BeamML_PyTorch_pytorchruninference/beamml_runinference_mean_load_model_latency_milli_secs' AND $timeFilter GROUP BY time($__interval), \"metric\"",
+ "rawQuery": true,
+ "refId": "B",
+ "resultFormat": "time_series",
+ "select": [
+ [
+ {
+ "params": [
+ "value"
+ ],
+ "type": "field"
+ },
+ {
+ "params": [],
+ "type": "mean"
+ }
+ ]
+ ],
+ "tags": []
}
],
"thresholds": [],
"timeFrom": null,
"timeRegions": [],
"timeShift": null,
- "title": "Pytorch RunInference Image Classification - ResNet 101 - Mean Model Load Time",
+ "title": "Pytorch RunInference Language Modeling using Bert From HuggingFace - Mean Load Model Latency",
"tooltip": {
"shared": true,
"sort": 0,
@@ -119,7 +1015,8 @@
},
"yaxes": [
{
- "format": "s",
+ "$$hashKey": "object:72",
+ "format": "ms",
"label": null,
"logBase": 1,
"max": null,
@@ -127,6 +1024,7 @@
"show": true
},
{
+ "$$hashKey": "object:73",
"format": "short",
"label": null,
"logBase": 1,
@@ -141,9 +1039,12 @@
}
}
],
- "schemaVersion": 22,
+ "refresh": false,
+ "schemaVersion": 30,
"style": "dark",
- "tags": ["performance tests"],
+ "tags": [
+ "performance tests"
+ ],
"templating": {
"list": []
},
@@ -168,8 +1069,5 @@
"timezone": "",
"title": "Python ML RunInference Benchmarks",
"uid": "1cnwVDkGk",
- "variables": {
- "list": []
- },
- "version": 2
+ "version": 47
}