Update LLMKube description to reflect pluggable runtime backends

Signed-off-by: Christopher Maher <defilan@users.noreply.github.com>

Author: Defilan

software/llmkube.yml

@@ -1,7 +1,7 @@
 name: LLMKube
 website_url: https://llmkube.com
 source_code_url: https://github.com/defilantech/LLMKube
-description: Kubernetes operator for llama.cpp-native LLM inference with GPU scheduling, Apple Silicon Metal support, and OpenAI-compatible API.
+description: Kubernetes operator for LLM inference with pluggable runtimes (llama.cpp, PersonaPlex/Moshi, generic), multi-GPU sharding, NVIDIA CUDA and Apple Silicon Metal support, and OpenAI-compatible API.
 licenses:
   - Apache-2.0
 platforms:
@@ -10,13 +10,13 @@ platforms:
   - K8S
 tags:
   - Generative Artificial Intelligence (GenAI)
-stargazers_count: 40
-updated_at: '2026-04-01'
+stargazers_count: 45
+updated_at: '2026-04-10'
 archived: false
 current_release:
-  tag: v0.5.3
-  published_at: '2026-04-01'
+  tag: v0.6.0
+  published_at: '2026-04-08'
 commit_history:
   2026-02: 40
   2026-03: 42
-  2026-04: 5
+  2026-04: 15