Mathis/llamactl
1
0
Fork 0
mirror of https://github.com/lordmathis/llamactl.git synced 2025-12-24 18:14:24 +00:00
Code Issues Packages Projects Releases Wiki Activity

Deployed e7baeb9 to dev with MkDocs 1.6.1 and mike 2.1.3

Browse Source
This commit is contained in:
lordmathis
2025-12-22 20:24:17 +00:00
parent fb85f41e6e
commit f38dda4e72
5 changed files with 140 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
dev/index.html
View File

@@ -678,6 +678,7 @@
<h2 id="features">Features<a class="headerlink" href="#features" title="Permanent link">&para;</a></h2>
<p><strong>🚀 Easy Model Management</strong><br />
- <strong>Multiple Models Simultaneously</strong>: Run different models at the same time (7B for speed, 70B for quality)<br />
- <strong>Dynamic Multi-Model Instances</strong>: llama.cpp router mode - serve multiple models from a single instance with on-demand loading<br />
- <strong>Smart Resource Management</strong>: Automatic idle timeout, LRU eviction, and configurable instance limits<br />
- <strong>Web Dashboard</strong>: Modern React UI for managing instances, monitoring health, and viewing logs </p>
<p><strong>🔗 Flexible Integration</strong><br />