Skip to content

use achieved_rate in the report graph.#232

Merged
achandrasekar merged 2 commits into
kubernetes-sigs:mainfrom
zetxqx:achievedrate
Oct 6, 2025
Merged

use achieved_rate in the report graph.#232
achandrasekar merged 2 commits into
kubernetes-sigs:mainfrom
zetxqx:achievedrate

Conversation

@zetxqx

@zetxqx zetxqx commented Sep 23, 2025

Copy link
Copy Markdown
Contributor

The current analyze plot is generated based on the expected rate. This may undercover some setup mistake while doing the analysis. Changed to achieved_rate

@k8s-ci-robot k8s-ci-robot added the cncf-cla: yes Indicates the PR's author has signed the CNCF CLA. label Sep 23, 2025
@k8s-ci-robot k8s-ci-robot added the size/XS Denotes a PR that changes 0-9 lines, ignoring generated files. label Sep 23, 2025

@achandrasekar achandrasekar left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Change looks good. Can you add a comment how this was tested? Config used + an example generated graph should be good.

Comment thread inference_perf/analysis/analyze.py
@zetxqx

zetxqx commented Oct 4, 2025

Copy link
Copy Markdown
Contributor Author

Change looks good. Can you add a comment how this was tested? Config used + an example generated graph should be good.

Config:

config:
  load:
    type: poisson
    stages:
      # Warmup — seat residents (~1×S)
      - rate: 15
        duration: 50            # 15*50  = 750

      # Main ladder
      - rate: 3
        duration: 20
      - rate: 10
        duration: 20
      - rate: 15
        duration: 20
      - rate: 20
        duration: 38           
      - rate: 22
        duration: 34           
      - rate: 25
        duration: 30           
      - rate: 30
        duration: 25           
      - rate: 35
        duration: 21           
      - rate: 40               
        duration: 38           
      - rate: 43
        duration: 36           
      - rate: 46
        duration: 33           
      - rate: 49
        duration: 30           
      - rate: 52
        duration: 29           
      - rate: 55
        duration: 27           
      - rate: 57
        duration: 26           
      - rate: 60
        duration: 25           
      
  api:
    type: completion
    streaming: true

  server:
    type: vllm
    model_name: Qwen/Qwen3-32B
    base_url: <redacted>
    ignore_eos: true

  tokenizer:
    pretrained_model_name_or_path: Qwen/Qwen3-32B

  data:
    type: shared_prefix
    shared_prefix:
      num_groups: 150
      num_prompts_per_group: 5
      system_prompt_len: 6000
      question_len: 1200
      output_len: 1000

  report:
    request_lifecycle:
      summary: true
      per_stage: true
      per_request: true

  storage:
    google_cloud_storage:
      bucket_name: "redacted"
      path: "redacted"

results:
image
image
image

@achandrasekar

Copy link
Copy Markdown
Contributor

/lgtm
/approve

@k8s-ci-robot k8s-ci-robot added the lgtm "Looks good to me", indicates that a PR is ready to be merged. label Oct 6, 2025
@k8s-ci-robot

Copy link
Copy Markdown
Contributor

[APPROVALNOTIFIER] This PR is APPROVED

This pull-request has been approved by: achandrasekar, zetxqx

The full list of commands accepted by this bot can be found here.

The pull request process is described here

Details Needs approval from an approver in each of these files:

Approvers can indicate their approval by writing /approve in a comment
Approvers can cancel approval by writing /approve cancel in a comment

@k8s-ci-robot k8s-ci-robot added the approved Indicates a PR has been approved by an approver from all required OWNERS files. label Oct 6, 2025
@achandrasekar achandrasekar merged commit 86b7ffb into kubernetes-sigs:main Oct 6, 2025
3 of 4 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

approved Indicates a PR has been approved by an approver from all required OWNERS files. cncf-cla: yes Indicates the PR's author has signed the CNCF CLA. lgtm "Looks good to me", indicates that a PR is ready to be merged. size/XS Denotes a PR that changes 0-9 lines, ignoring generated files.

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants