noonghunna/club-3090

v0.4.0 Feature

This release adds 3 notable features for engineering teams evaluating rollout.

Published 23d Model Serving & MLOps

✓ No known CVEs patched

✓ No known CVEs patched in this version

Summary

AI summary

Updates ✨ Features, 🐛 Bug fixes, and rebench across a mixed release.

Full changelog

feat(rebench-report): close 9 gaps — TL;DR + rig + timings + reproducer + delta + discuss variant (be7f9aa)
feat(rebench): add REPORT.md synthesizer + container/boot/GPU captures (18355f4)
feat(rebench): halve default soak to 10 sessions × 5 turns (~15-20 min) (3406894)
feat(rebench): one-shot canonical 5-step bench orchestrator (94a2522)

fix(switch): GPU memory pre-flight + widen RUNNING_PATTERN (4866913)
fix(rebench-report): parse aider upstream_per_exercise as dict (not list) (7c4b310)

bench(head-to-head): matched-config rebench + Qwen INT8 PTH KV compose (755e519)

docs(gemma-4-31b): document TQ3 Ampere FA2 head_dim wall + vendor #40108 overlay (f8c7066)
docs(benchmarks): Qwen 3.6 27B vs Gemma 4 31B head-to-head on dual 3090 (edda3b3)

chore(composes): bump Qwen pins → 1acd67a7, drop obsolete patch_tolist_cudagraph (16a1374)
chore(cliff): skip auto-regen bot commits in changelog parser (a258e49)

[Pin: git checkout v0.4.0] · Full diff

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

Track noonghunna/club-3090

Get notified when new releases ship.

About noonghunna/club-3090

v0.8.7 Genesis vLLM composes deprecated; default to `vllm/minimal`.
v0.8.6 Compose paths moved to `models/<model>/<engine>/compose/<topology>/<quant>/<serving>.yml`.