From a4d0f8874fc9d4fc08d588c962f3aa5a5c40d7b0 Mon Sep 17 00:00:00 2001 From: "github-actions[bot]" <41898282+github-actions[bot]@users.noreply.github.com> Date: Sun, 19 Jul 2026 16:28:51 +0000 Subject: [PATCH] chore: release 0.9.8 Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> --- .release-please-manifest.json | 2 +- CHANGELOG.md | 25 +++++++++++++++++++++++++ Makefile | 2 +- charts/foreman/Chart.yaml | 4 ++-- charts/llmkube/Chart.yaml | 4 ++-- pkg/cli/version.go | 2 +- 6 files changed, 32 insertions(+), 7 deletions(-) diff --git a/.release-please-manifest.json b/.release-please-manifest.json index 755d7b47..c206008b 100644 --- a/.release-please-manifest.json +++ b/.release-please-manifest.json @@ -1,3 +1,3 @@ { - ".": "0.9.7" + ".": "0.9.8" } diff --git a/CHANGELOG.md b/CHANGELOG.md index cf828e16..ba464222 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -5,6 +5,31 @@ All notable changes to LLMKube will be documented in this file. The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/), and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html). +## [0.9.8](https://github.com/defilantech/LLMKube/compare/v0.9.7...v0.9.8) (2026-07-19) + + +### Features + +* **controller:** add InferenceService hardware-labels info metric ([#1121](https://github.com/defilantech/LLMKube/issues/1121)) ([#1160](https://github.com/defilantech/LLMKube/issues/1160)) ([039adaa](https://github.com/defilantech/LLMKube/commit/039adaa926b76eb31bc36a512ea82e1ee70dd511)) +* **controller:** add llamacpp-router runtime for multi-model serving ([#1152](https://github.com/defilantech/LLMKube/issues/1152)) ([fae5983](https://github.com/defilantech/LLMKube/commit/fae5983242226dd70eb1345c221b1188072b6d27)) +* **controller:** explicit vllm serve entrypoint for image-agnostic vLLM ([#1164](https://github.com/defilantech/LLMKube/issues/1164)) ([#1165](https://github.com/defilantech/LLMKube/issues/1165)) ([3eeb580](https://github.com/defilantech/LLMKube/commit/3eeb580f31d6ac47c265b447638fdfbd2f92b0c3)) +* **controller:** pass staged model directory to vLLM/SGLang for multi-file models ([#1157](https://github.com/defilantech/LLMKube/issues/1157)) ([#1159](https://github.com/defilantech/LLMKube/issues/1159)) ([a24fa94](https://github.com/defilantech/LLMKube/commit/a24fa948038561d3e5b80ec0da84038844688c37)) +* **controller:** ROCm/HIP runtime tier for AMD nodes ([#701](https://github.com/defilantech/LLMKube/issues/701)) ([#1154](https://github.com/defilantech/LLMKube/issues/1154)) ([3704d47](https://github.com/defilantech/LLMKube/commit/3704d476fa650449598330ca4b91950bdc3c7ed0)) +* **finalize:** gate foreman-finalize on the Foreman verify verdict ([#1150](https://github.com/defilantech/LLMKube/issues/1150)) ([#1153](https://github.com/defilantech/LLMKube/issues/1153)) ([5c7b2cd](https://github.com/defilantech/LLMKube/commit/5c7b2cde7476c24dee0507d082e3751236385588)) +* **foreman:** in-executor envtest gate feedback loop ([#768](https://github.com/defilantech/LLMKube/issues/768)) ([#1135](https://github.com/defilantech/LLMKube/issues/1135)) ([074544a](https://github.com/defilantech/LLMKube/commit/074544a64ec35c9fe08ed8e5b003b22799947f19)) +* **foreman:** provider-neutral CodeHost/WorkItems/ChangePolicy seams ([#1158](https://github.com/defilantech/LLMKube/issues/1158)) ([#1161](https://github.com/defilantech/LLMKube/issues/1161)) ([d3a8ad6](https://github.com/defilantech/LLMKube/commit/d3a8ad65b36375ef7808d8c3f0f52b72282efdfd)) +* **observability:** per-InferenceService SLO declaration via Pyrra ([#415](https://github.com/defilantech/LLMKube/issues/415)) ([#1149](https://github.com/defilantech/LLMKube/issues/1149)) ([4ae022c](https://github.com/defilantech/LLMKube/commit/4ae022cc862ed0200ba4ea51727324a06fa51166)) + + +### Bug Fixes + +* bump boilerplate copyright year 2025 -> 2026 ([#1162](https://github.com/defilantech/LLMKube/issues/1162)) ([#1163](https://github.com/defilantech/LLMKube/issues/1163)) ([30dfaf2](https://github.com/defilantech/LLMKube/commit/30dfaf22958b8cd2d9aa98a58af4a1bd0d24da09)) + + +### Documentation + +* document strict-taint model caches ([#1132](https://github.com/defilantech/LLMKube/issues/1132)) ([9250996](https://github.com/defilantech/LLMKube/commit/9250996c42f377dfd2915cfded6fbb219d3fe7ce)) + ## [0.9.7](https://github.com/defilantech/LLMKube/compare/v0.9.6...v0.9.7) (2026-07-16) diff --git a/Makefile b/Makefile index 9dd0d61b..c8b91029 100644 --- a/Makefile +++ b/Makefile @@ -1,5 +1,5 @@ # Image URL to use all building/pushing image targets -IMG ?= ghcr.io/defilantech/llmkube-controller:0.9.7 # x-release-please-version +IMG ?= ghcr.io/defilantech/llmkube-controller:0.9.8 # x-release-please-version # Get the currently used golang install path (in GOPATH/bin, unless GOBIN is set) ifeq (,$(shell go env GOBIN)) diff --git a/charts/foreman/Chart.yaml b/charts/foreman/Chart.yaml index f856951c..1b4a2d05 100644 --- a/charts/foreman/Chart.yaml +++ b/charts/foreman/Chart.yaml @@ -10,8 +10,8 @@ description: | coupling is that the foreman-operator's RBAC reads inference.llmkube.dev CRDs that llmkube installs. type: application -version: 0.9.7 -appVersion: 0.9.7 +version: 0.9.8 +appVersion: 0.9.8 keywords: - llmkube - foreman diff --git a/charts/llmkube/Chart.yaml b/charts/llmkube/Chart.yaml index 6083f3ad..6eb94652 100644 --- a/charts/llmkube/Chart.yaml +++ b/charts/llmkube/Chart.yaml @@ -4,8 +4,8 @@ description: >- A Helm chart for LLMKube - Kubernetes operator for GPU-accelerated LLM inference type: application -version: 0.9.7 -appVersion: 0.9.7 +version: 0.9.8 +appVersion: 0.9.8 keywords: - llm - kubernetes diff --git a/pkg/cli/version.go b/pkg/cli/version.go index f0c11f8a..0c89c2d7 100644 --- a/pkg/cli/version.go +++ b/pkg/cli/version.go @@ -24,7 +24,7 @@ import ( var ( // Version is set during build via ldflags or updated by release-please - Version = "0.9.7" // x-release-please-version + Version = "0.9.8" // x-release-please-version // GitCommit is set during build GitCommit = "unknown" // BuildDate is set during build