Skip to content

Pull requests: kubernetes-sigs/inference-perf

New pull request New
31 Open 280 Closed
31 Open 280 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

Address JOSS paper reviewer feedback: clarify extensions sentence, co… 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. needs-rebase Indicates a PR cannot be merged because it has merge conflicts with HEAD. size/M Denotes a PR that changes 30-99 lines, ignoring generated files.
#534 opened Jun 5, 2026 by jjk-g Collaborator Loading…
3
fix: preserve partial response body when a streaming request fails 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.
#530 opened Jun 4, 2026 by Bslabe123 Contributor Loading…
1
Test/optional live tier 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.
#529 opened Jun 3, 2026 by Bslabe123 Contributor Loading…
1
Add absolute coverage metrics, artifacts, badge. cncf-cla: yes Indicates the PR's author has 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/L Denotes a PR that changes 100-499 lines, ignoring generated files.
#527 opened Jun 3, 2026 by Bslabe123 Contributor Loading…
2
cleanup: Start load generator workers with forkserver instead of fork 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.
#526 opened Jun 3, 2026 by Bslabe123 Contributor Loading…
1
Add Support for VisionArena Dataset 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.
#525 opened Jun 1, 2026 by Bslabe123 Contributor Loading…
1
Support multi-tenant headers and OTel mapping 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.
#523 opened Jun 1, 2026 by LukeAVanDrie Contributor Loading…
2
[WIP] Add unit tests for the split config package 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.
#520 opened May 28, 2026 by Bslabe123 Contributor • Draft
3
Refactor and improve max-model-len truncation to be more efficient 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. size/L Denotes a PR that changes 100-499 lines, ignoring generated files.
#512 opened May 28, 2026 by achandrasekar Contributor Loading…
1
1
Inject session identity header for session replay requests 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.
#504 opened May 22, 2026 by pavanipenumalla Loading…
1
13
Update OWNERS_ALIASES 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/invalid-owners-file Indicates that a PR should not merge because it has an invalid OWNERS file in it. 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.
#503 opened May 22, 2026 by achandrasekar Contributor Loading…
@Bslabe123
4
Emit Prometheus merics for runtime observability 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.
#501 opened May 21, 2026 by Bslabe123 Contributor Loading…
1
[WIP] Add config for constraining media pool 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.
#500 opened May 21, 2026 by Bslabe123 Contributor • Draft
2
[conversation_replay] force min_tokens == max_tokens for deterministic output length 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/M Denotes a PR that changes 30-99 lines, ignoring generated files.
#497 opened May 20, 2026 by LoganVegnaSHOP Contributor Loading…
4
[WIP] Add support for ShareGpt4Video Dataset 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.
#494 opened May 18, 2026 by Bslabe123 Contributor • Draft
3
[WIP] Add MMMU Dataset cncf-cla: no Indicates the PR's author has not 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.
#478 opened May 12, 2026 by Bslabe123 Contributor • Draft
3
Emit native llm-d-benchmark v0.2 partial reports alongside existing reports cncf-cla: yes Indicates the PR's author has signed the CNCF CLA. do-not-merge/hold Indicates that a PR should not merge because someone has issued a /hold command. do-not-merge/invalid-commit-message Indicates that a PR should not merge because it has an invalid commit message. size/XXL Denotes a PR that changes 1000+ lines, ignoring generated files.
#461 opened Apr 29, 2026 by Bslabe123 Contributor Loading…
3
Security: Archive extraction vulnerable to path traversal (TarSlip) cncf-cla: no Indicates the PR's author has not signed the CNCF CLA. lgtm "Looks good to me", indicates that a PR is ready to be merged. size/S Denotes a PR that changes 10-29 lines, ignoring generated files.
#451 opened Apr 25, 2026 by tomaioo Loading…
@Bslabe123
7
[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
[WIP] Add Expressions API 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.
#423 opened Apr 9, 2026 by Bslabe123 Contributor • Draft
2
[WIP] Add --url Flag and Config Autofilling Logic cncf-cla: no Indicates the PR's author has not 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/XL Denotes a PR that changes 500-999 lines, ignoring generated files.
#384 opened Apr 1, 2026 by Bslabe123 Contributor • Draft
2
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…
12
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
[WIP] Fix saturation detection and harden load generator 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/XXL Denotes a PR that changes 1000+ lines, ignoring generated files.
#360 opened Mar 2, 2026 by Bslabe123 Contributor • Draft
9
ProTip! Type g p on any issue or pull request to go back to the pull request listing page.