Skip to content

Pull requests: kubernetes-sigs/inference-perf

New pull request New
19 Open 241 Closed
19 Open 241 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

[WIP] feat: Implement distributed Redis-based load generator 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. do-not-merge/work-in-progress Indicates that a PR should not merge because it is a work in progress. needs-rebase Indicates a PR cannot be merged because it has merge conflicts with HEAD. size/XXL Denotes a PR that changes 1000+ lines, ignoring generated files.
#438 opened Apr 14, 2026 by jjk-g Collaborator Loading…
1
5
Extract common graph-backed session replay runtime into ReplayGraphSessionGeneratorBase cncf-cla: yes Indicates the PR's author has signed the CNCF CLA. size/XXL Denotes a PR that changes 1000+ lines, ignoring generated files.
#436 opened Apr 14, 2026 by alonh Contributor Loading…
3
Improve build_graph runtime in otel_trace_to_replay_graph.py cncf-cla: yes Indicates the PR's author has signed the CNCF CLA. size/L Denotes a PR that changes 100-499 lines, ignoring generated files.
#434 opened Apr 14, 2026 by lenadankin Contributor Loading…
3
workaround unexpected sharegpt format change cncf-cla: yes Indicates the PR's author has signed the CNCF CLA. size/M Denotes a PR that changes 30-99 lines, ignoring generated files.
#433 opened Apr 13, 2026 by diamondburned Contributor Loading…
8
fix: streaming response body consumed before SSE parser cncf-cla: yes Indicates the PR's author has signed the CNCF CLA. needs-rebase Indicates a PR cannot be merged because it has merge conflicts with HEAD. size/L Denotes a PR that changes 100-499 lines, ignoring generated files.
#421 opened Apr 9, 2026 by LoganVegnaSHOP Contributor Loading…
5
Add E2e testing for Prometheus Querying and Report Contents cncf-cla: yes Indicates the PR's author has signed the CNCF CLA. size/L Denotes a PR that changes 100-499 lines, ignoring generated files.
#413 opened Apr 6, 2026 by Bslabe123 Contributor Loading…
8
Derive TPOT, ITL from Repsonse Tokens, not Chunks cncf-cla: yes Indicates the PR's author has signed the CNCF CLA. size/L Denotes a PR that changes 100-499 lines, ignoring generated files.
#410 opened Apr 3, 2026 by Bslabe123 Contributor Loading…
5
Add --url Flag and Config Autofilling Logic cncf-cla: yes Indicates the PR's author has signed the CNCF CLA. size/XL Denotes a PR that changes 500-999 lines, ignoring generated files.
#384 opened Apr 1, 2026 by Bslabe123 Contributor Loading…
1
Fix SharedPrefix Datagen Prompt Length cncf-cla: yes Indicates the PR's author has signed the CNCF CLA. size/XL Denotes a PR that changes 500-999 lines, ignoring generated files.
#383 opened Apr 1, 2026 by Bslabe123 Contributor Loading…
8
Cleanup Prometheus Metric Querying cncf-cla: yes Indicates the PR's author has signed the CNCF CLA. size/XXL Denotes a PR that changes 1000+ lines, ignoring generated files.
#382 opened Apr 1, 2026 by Bslabe123 Contributor Loading…
2
Shared Prefix Trace Replay & Tree-of-Thought Generation cncf-cla: yes Indicates the PR's author has signed the CNCF CLA. needs-rebase Indicates a PR cannot be merged because it has merge conflicts with HEAD. size/XL Denotes a PR that changes 500-999 lines, ignoring generated files.
#369 opened Mar 25, 2026 by diamondburned Contributor Loading…
2
Add wg-sreving serving catalog 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/XXL Denotes a PR that changes 1000+ lines, ignoring generated files.
#368 opened Mar 24, 2026 by jjk-g Collaborator Loading…
@SachinVarghese
2
Fix saturation detection and harden load generator cncf-cla: yes Indicates the PR's author has signed the CNCF CLA. size/XXL Denotes a PR that changes 1000+ lines, ignoring generated files.
#360 opened Mar 2, 2026 by Bslabe123 Contributor Loading…
9
fix: handle ShareGPT dataset exhaustion by reinitializing iterator cncf-cla: yes Indicates the PR's author has signed the CNCF CLA. size/L Denotes a PR that changes 100-499 lines, ignoring generated files.
#359 opened Feb 27, 2026 by DebuggingMax Loading…
1
8
[WIP] Add raw time series metric output. 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. do-not-merge/work-in-progress Indicates that a PR should not merge because it is a work in progress. size/L Denotes a PR that changes 100-499 lines, ignoring generated files.
#356 opened Feb 25, 2026 by jjk-g Collaborator Loading…
5
Fix ShareGPT StopIteration error on dataset exhaustion cncf-cla: no Indicates the PR's author has not signed the CNCF CLA. do-not-merge/invalid-commit-message Indicates that a PR should not merge because it has an invalid commit message. size/M Denotes a PR that changes 30-99 lines, ignoring generated files.
#341 opened Feb 4, 2026 by loganionian Loading…
1
9
feat: Add Chat Completion API support to SharedPrefixDataGenerator 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/L Denotes a PR that changes 100-499 lines, ignoring generated files.
#287 opened Nov 19, 2025 by bongwoobak Loading…
@Bslabe123
18
Support setting custom y-axis limits optionally cncf-cla: yes Indicates the PR's author has signed the CNCF CLA. kind/failing-test Categorizes issue or PR as related to a consistently or frequently failing test. needs-rebase Indicates a PR cannot be merged because it has merge conflicts with HEAD. size/S Denotes a PR that changes 10-29 lines, ignoring generated files.
#268 opened Nov 3, 2025 by Shuwen-Fang Contributor Loading…
@Bslabe123
7
refactor: Make base client concrete and usable cncf-cla: yes Indicates the PR's author has signed the CNCF CLA. kind/failing-test Categorizes issue or PR as related to a consistently or frequently failing test. size/L Denotes a PR that changes 100-499 lines, ignoring generated files.
#246 opened Oct 7, 2025 by LukeAVanDrie Contributor Loading…
11
ProTip! Adding no:label will show everything without a label.