Skip to content

noonghunna/club-3090

v0.8.6 Breaking

This release includes 1 breaking change for platform teams planning a safe upgrade.

Published 8d Model Serving & MLOps
✓ No known CVEs patched
Read the diff → Tool health → What is this tool? →

✓ No known CVEs patched in this version

ReleasePort's take

Moderate signal
editorial:auto 7d

Compose path locations have changed to `models/<model>/<engine>/compose/<topology>/<quant>/<serving>.yml`. Update configuration files accordingly.

Why it matters: Affects configuration layout; requires manual adjustment of paths before deployment. Severity score 80 indicates high impact.

Summary

AI summary

Updates 🐛 Bug fixes, 📝 Documentation, and 🧹 Maintenance across a mixed release.

Changes in this release

Breaking High

Compose paths moved to `models/<model>/<engine>/compose/<topology>/<quant>/<serving>.yml`.

Compose paths moved to `models/<model>/<engine>/compose/<topology>/<quant>/<serving>.yml`.

Source: llm_adapter@2026-05-28

Confidence: high

 —
Feature Medium

Adds PRISM-PRO-DQ and APEX-MTP presets for ik-llama conforming to the <quant>/ layout.

Adds PRISM-PRO-DQ and APEX-MTP presets for ik-llama conforming to the <quant>/ layout.

Source: llm_adapter@2026-05-28

Confidence: high

 —
Dependency Medium

Pins vllm/dual to stable version 0.21.0 and drops all source overlays (issue #407).

Pins vllm/dual to stable version 0.21.0 and drops all source overlays (issue #407).

Source: llm_adapter@2026-05-28

Confidence: high

 —
Bugfix Medium

Fixes compatibility catalog to cover new ik-llama PRISM/APEX presets.

Fixes compatibility catalog to cover new ik-llama PRISM/APEX presets.

Source: llm_adapter@2026-05-28

Confidence: high

 —
Bugfix Medium

Fixes post‑PR compose‑path issues in gpu-mode.sh and updates two README patches.

Fixes post‑PR compose‑path issues in gpu-mode.sh and updates two README patches.

Source: llm_adapter@2026-05-28

Confidence: high

 —
Bugfix Medium

Syncs vision defaults to the 2026‑05‑25 re‑tune (issue #438).

Syncs vision defaults to the 2026‑05‑25 re‑tune (issue #438).

Source: llm_adapter@2026-05-28

Confidence: high

 —
Bugfix Medium

Re‑tunes single‑card vision defaults to measured‑safe limits (1 M‑px, 160 K/150 K).

Re‑tunes single‑card vision defaults to measured‑safe limits (1 M‑px, 160 K/150 K).

Source: llm_adapter@2026-05-28

Confidence: high

 —
Bugfix Low

Corrects ik-llama/iq4ks-mtp usage comment from 262K to 200K in switch documentation.

Corrects ik-llama/iq4ks-mtp usage comment from 262K to 200K in switch documentation.

Source: granite4.1:30b@2026-05-28-audit

Confidence: low

 —
Full changelog

⚠️ Breaking — compose paths moved. Composes now live at models/<model>/<engine>/compose/<topology>/<quant>/<serving>.yml (e.g. dual/autoround-int4/fp8-mtp.yml). Raw pre-v0.8.6 paths (dual/turbo.yml, docker-compose.yml, …) no longer resolve. Use the --variant keys — bash scripts/launch.sh vllm/default (topology-autodetect), vllm/dual, ik-llama/iq4ks-mtp, … — or the new <quant>/ paths directly. launch.sh/switch.sh now derive from the registry (single source of truth) and accept <engine>/default + <engine>/<topology>/default.

v0.8.6 — 2026-05-26

✨ Features

  • feat(ik-llama): PRISM-PRO-DQ + APEX-MTP presets, conformed to the / layout (458c473)

🐛 Bug fixes

  • fix(profiles): cover the new ik-llama PRISM/APEX presets in the compat catalog (aa2a965)
  • fix: post-PR-A compose-path fixes for gpu-mode.sh + 2 patch READMEs (b23846e)
  • fix(registry+bench): sync vision defaults to the 2026-05-25 re-tune (#438) (b116750)
  • fix(vision): re-tune single-card vision defaults to measured-safe (1M-px + 160K/150K) (c9b7dd3)
  • fix(vllm/dual): pin to stable v0.21.0, drop all source overlays (#407 pin-drift) (cf1f14f)

📝 Documentation

  • docs+scripts: finish / path migration across full repo sweep (eaa7a8c)
  • docs(switch): correct ik-llama/iq4ks-mtp usage comment 262K -> 200K (2135230)

🧹 Maintenance

  • refactor(launch): derive launcher tables from the registry + /default resolver (a0520e2)
  • refactor(compose): insert layer + make the registry the single source of truth (9821c94)

[Pin: git checkout v0.8.6] · Full diff

Breaking Changes

  • Compose paths moved to `models/**compose**/*.yml`; previous raw paths (e.g., `dual/turbo.yml`, `docker-compose.yml`) no longer resolve. Use `--variant` keys such as `bash scripts/launch.sh vllm/default`, `vllm/dual`, `ik-llama/iq4ks-mtp` or the new `/` paths directly.
View diff on GitHub

Weekly OSS security release digest.

The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.

No spam, unsubscribe anytime.

Share this release

Share on X Share on Bluesky

Track noonghunna/club-3090

Get notified when new releases ship.

Sign up free

About noonghunna/club-3090

All releases →

Related context

Earlier breaking changes

  • v0.8.7 Genesis vLLM composes deprecated; default to `vllm/minimal`.

Beta — feedback welcome: [email protected]