Skip to content

[Klaud Cold] Update kimik2.5-int4-b300-vllm vLLM image to v0.21.0 #1457

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
functionstackx merged 3 commits into from
May 18, 2026
Merged

[Klaud Cold] Update kimik2.5-int4-b300-vllm vLLM image to v0.21.0 #1457

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
6933092
Update kimik2.5-int4-b300-vllm vLLM image to v0.21.0
functionstackx May 17, 2026
b3dd2d7
chore: fill pr-link for #1457
functionstackx May 17, 2026
d424deb
Merge branch 'main' into update-kimik2.5-int4-b300-vllm-v0.21.0
functionstackx May 18, 2026
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
2 changes: 1 addition & 1 deletion .github/configs/nvidia-master.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2569,7 +2569,7 @@ kimik2.5-int4-b200-vllm-agentic:
# Kimi-K2.5 INT4 B200 vLLM recipe as-is until B300-specific tuning is available.

kimik2.5-int4-b300-vllm:
image: vllm/vllm-openai:v0.20.0-cu130
image: vllm/vllm-openai:v0.21.0
model: moonshotai/Kimi-K2.5
model-prefix: kimik2.5
runner: b300
Expand Down
6 changes: 6 additions & 0 deletions perf-changelog.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2796,3 +2796,9 @@
description:
- "Update vLLM image from v0.20.2 (1d old) to v0.21.0"
pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1466

- config-keys:
- kimik2.5-int4-b300-vllm
description:
- "Update vLLM image from v0.20.0-cu130 (14d old) to v0.21.0"
pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1457
Comment on lines +2801 to +2804
Copy link
Copy Markdown
Contributor

@claude claude Bot May 17, 2026

Choose a reason for hiding this comment

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

🟡 The changelog entry's description includes an inconsistent (14d old) parenthetical that doesn't appear in any other entry in perf-changelog.yaml. Every other description in the file uses the clean pattern Update {vLLM,SGLang,vLLM ROCm} image from vA to vB, and the 14d age is relative to PR creation time so it becomes meaningless after merge. Suggest changing the description to "Update vLLM image from v0.20.0-cu130 to v0.21.0" for consistency.

Extended reasoning...

What the issue is

The new entry added at perf-changelog.yaml lines 2632–2637 contains the description:

- "Update vLLM image from v0.20.0-cu130 (14d old) to v0.21.0"

The (14d old) parenthetical is unique to this entry. Every other description in perf-changelog.yaml follows the clean pattern Update {vLLM,SGLang,vLLM ROCm} image from vA to vB with no age annotation — see for example the immediately preceding entries at lines 2581, 2587, 2593, 2599, 2605, 2611, 2618, 2624, and 2630.

Proof / verification

Running grep -nE '\([0-9]+d old\)' perf-changelog.yaml returns exactly one match: the new line 2636 added by this PR. The same (14d old) phrasing appears in the PR description ("Bumps kimik2.5-int4-b300-vllm from vllm/vllm-openai:v0.20.0-cu130 (14d old) to ..."), strongly suggesting it leaked into the changelog from the automated PR-generation pipeline that produces both the PR body and the changelog entry.

Why it doesn't belong here

perf-changelog.yaml is a persistent, user-facing record of image bumps. "14 days old" is a value measured relative to PR creation time on 2026-05-17 — once merged, the relative age becomes meaningless and even misleading (a reader six months from now has no way to interpret it). The PR body is the right place for that context; the durable changelog should match the established pattern.

Impact

Cosmetic / consistency only — no runtime effect. Worth fixing because the changelog is the canonical reference for these bumps and it's a one-line edit.

Fix

Change line 2636 to:

    - "Update vLLM image from v0.20.0-cu130 to v0.21.0"

Loading