The busy figure is nvidia-smi's utilization.gpu: the share of time any kernel ran, which a kernel on one SM fills. On cuda01 decode read 92% busy while the SMs had work 69% of the time and issued on 18% of their cycles. Busy is now said to be that, and beside it: each card's draw against its power limit (efficiency table, fleet and node charts, the console's GPU work chart), and where the profiling counters can be read, SMs active, SM occupancy, tensor cores and DRAM (llmgw_gpu_*_active_percent), from NVML's GPM on Hopper and later or a dcgm-exporter on the node (discovery.dcgm_exporter). The GPU map colours by work by default and keeps busy as a mode. A MIG instance is never published with its card's profile. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
1 parent
7bfe70c8df
commit
c866b3a8ee
34 files changed
+954
-52
No files matched your search
@@ -13,8 +13,13 @@ type modelEfficiency struct {
|
||||
// TokensPerSec is output tokens a second; GPUs the cards it holds now.
|
||||
TokensPerSec float64
|
||||
GPUs float64
|
||||
// Watts is what those cards draw; Util their average utilisation.
|
||||
Watts, Util float64
|
||||
// Watts is what those cards draw; Util the average share of time a
|
||||
// kernel ran on them, which says nothing of how much of each chip it ran
|
||||
// on. PowerLoad (draw against the power limit) and SMActive (the SMs'
|
||||
// share of time with work, where GPM or DCGM reads it) are how much, in
|
||||
// percent; -1 is not known.
|
||||
Watts, Util float64
|
||||
PowerLoad, SMActive float64
|
||||
// PerGPU and PerWh are the two ways of saying how much work the cards
|
||||
// do: output tokens a second per card, and per watt-hour drawn.
|
||||
PerGPU, PerWh float64
|
||||
@@ -34,6 +39,10 @@ var efficiencyQueries = []struct {
|
||||
func(e *modelEfficiency, v float64) { e.Watts = v }},
|
||||
{`avg by (model) (llmgw_gpu_utilization_percent * on (node, gpu) group_left (model) llmgw_gpu_assigned)`,
|
||||
func(e *modelEfficiency, v float64) { e.Util = v }},
|
||||
{`avg by (model) ((llmgw_gpu_power_watts / llmgw_gpu_power_limit_watts) * on (node, gpu) group_left (model) llmgw_gpu_assigned)`,
|
||||
func(e *modelEfficiency, v float64) { e.PowerLoad = 100 * v }},
|
||||
{`avg by (model) (llmgw_gpu_sm_active_percent * on (node, gpu) group_left (model) llmgw_gpu_assigned)`,
|
||||
func(e *modelEfficiency, v float64) { e.SMActive = v }},
|
||||
}
|
||||
|
||||
// loadEfficiency is the table, best per card first; nil when the metrics
|
||||
@@ -56,7 +65,7 @@ func loadEfficiency(ctx context.Context, h History) []modelEfficiency {
|
||||
}
|
||||
e := byModel[s.Name]
|
||||
if e == nil {
|
||||
e = &modelEfficiency{Model: s.Name}
|
||||
e = &modelEfficiency{Model: s.Name, PowerLoad: -1, SMActive: -1}
|
||||
byModel[s.Name] = e
|
||||
}
|
||||
q.into(e, s.Last())
|
||||
|
||||
Reference in new issue
Block a user