Skip to content

Cast bounds type in tests to func def: latency, interToken, and timeToFirst (to int) #163

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Aug 24, 2025
Merged

Cast bounds type in tests to func def: latency, interToken, and timeToFirst (to int) #163

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
25ba214
Cast bounds type in tests to func def: latency, interToken, and timeT…
pancak3 Aug 24, 2025
22aa3e6
Use float 32
pancak3 Aug 24, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
16 changes: 8 additions & 8 deletions pkg/llm-d-inference-sim/simulator_test.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -761,8 +761,8 @@ var _ = Describe("Simulator", func() {
simulator.config.InterTokenLatency = interTokenLatency
simulator.config.InterTokenLatencyStdDev = stddev
interToken := simulator.getInterTokenLatency()
Expect(interToken).To(BeNumerically(">=", float32(interTokenLatency)*0.3))
Expect(interToken).To(BeNumerically("<=", float32(interTokenLatency)*1.7))
Expect(interToken).To(BeNumerically(">=", int(float32(interTokenLatency)*0.3)))
Expect(interToken).To(BeNumerically("<=", int(float32(interTokenLatency)*1.7)))
},
func(interTokenLatency int, stddev int) string {
return fmt.Sprintf("interTokenLatency: %d stddev: %d", interTokenLatency, stddev)
Expand All @@ -778,8 +778,8 @@ var _ = Describe("Simulator", func() {
simulator.config.InterTokenLatency = interTokenLatency
simulator.config.InterTokenLatencyStdDev = stddev
latency := simulator.getTotalInterTokenLatency(numberOfTokens)
Expect(latency).To(BeNumerically(">=", float32(interTokenLatency)*0.3*float32(numberOfTokens)))
Expect(latency).To(BeNumerically("<=", float32(interTokenLatency)*1.7*float32(numberOfTokens)))
Expect(latency).To(BeNumerically(">=", int(float32(interTokenLatency)*0.3*float32(numberOfTokens))))
Expect(latency).To(BeNumerically("<=", int(float32(interTokenLatency)*1.7*float32(numberOfTokens))))
},
func(interTokenLatency int, stddev int, numberOfTokens int) string {
return fmt.Sprintf("interTokenLatency: %d stddev: %d, numberOfTokens: %d", interTokenLatency,
Expand All @@ -800,11 +800,11 @@ var _ = Describe("Simulator", func() {
simulator.config.KVCacheTransferLatencyStdDev = kvCacheLatencyStdDev
timeToFirst := simulator.getTimeToFirstToken(doREmotePrefill)
if doREmotePrefill {
Expect(timeToFirst).To(BeNumerically(">=", float32(kvCacheLatency)*0.3))
Expect(timeToFirst).To(BeNumerically("<=", float32(kvCacheLatency)*1.7))
Expect(timeToFirst).To(BeNumerically(">=", int(float32(kvCacheLatency)*0.3)))
Expect(timeToFirst).To(BeNumerically("<=", int(float32(kvCacheLatency)*1.7)))
} else {
Expect(timeToFirst).To(BeNumerically(">=", float32(timeToFirstToken)*0.3))
Expect(timeToFirst).To(BeNumerically("<=", float32(timeToFirstToken)*1.7))
Expect(timeToFirst).To(BeNumerically(">=", int(float32(timeToFirstToken)*0.3)))
Expect(timeToFirst).To(BeNumerically("<=", int(float32(timeToFirstToken)*1.7)))
}
},
func(timeToFirstToken int, timeToFirstTokenStdDev int,
Expand Down