Skip to content

[Bug] Possibly incorrect output dump ? (The actual data appears to be fine) #114

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.

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

Open
thameem-abbas opened this issue Apr 15, 2025 · 1 comment
Labels

Comments

@thameem-abbas
Copy link
Contributor

cat fp8_fp8_tp2.json | jq '.benchmarks[] | .args.profile.measured_rates'
[
  0.020927754394140415,
  1.277633358306354,
  0.16187661325946062,
  0.3006715892920996,
  0.42809462336187576,
  0.5790540149106302,
  0.706221702530327,
  0.8352987384060198,
  0.9707840531576964,
  1.0963631997951027
]
[
  0.020927754394140415,
  1.277633358306354,
  0.16187661325946062,
  0.3006715892920996,
  0.42809462336187576,
  0.5790540149106302,
  0.706221702530327,
  0.8352987384060198,
  0.9707840531576964,
  1.0963631997951027
]
[
  0.020927754394140415,
  1.277633358306354,
  0.16187661325946062,
  0.3006715892920996,
  0.42809462336187576,
  0.5790540149106302,
  0.706221702530327,
  0.8352987384060198,
  0.9707840531576964,
  1.0963631997951027
]
[
  0.020927754394140415,
  1.277633358306354,
  0.16187661325946062,
  0.3006715892920996,
  0.42809462336187576,
  0.5790540149106302,
  0.706221702530327,
  0.8352987384060198,
  0.9707840531576964,
  1.0963631997951027
]
....
....

--

cat fp8_fp8_tp2.json | jq '.benchmarks[] | .metrics.requests_per_second.successful.mean'

0.020927754394140415
1.277633358306354
0.16187661325946062
0.3006715892920996
0.42809462336187576
0.5790540149106302
0.706221702530327
0.8352987384060198
0.9707840531576964
1.0963631997951027

Looks like an unintentional referencing of the same object between benchmark runs ?

@rgreenberg1
Copy link
Collaborator

rgreenberg1 commented May 8, 2025

Action Item:
Strip this out from the output file.

@rgreenberg1 rgreenberg1 added the good first issue Good for newcomers label May 8, 2025
@rgreenberg1 rgreenberg1 moved this from Ready to Backlog in GuideLLM Kanban Board May 8, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
Projects
Status: Backlog
Development

No branches or pull requests

2 participants