mirror of
https://github.com/lordmathis/llamactl.git
synced 2025-12-22 17:14:22 +00:00
Deployed 470f900 to dev with MkDocs 1.6.1 and mike 2.1.3
This commit is contained in:
Binary file not shown.
Binary file not shown.
@@ -593,6 +593,15 @@
|
||||
</span>
|
||||
</a>
|
||||
|
||||
</li>
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="#data-directory-configuration" class="md-nav__link">
|
||||
<span class="md-ellipsis">
|
||||
Data Directory Configuration
|
||||
</span>
|
||||
</a>
|
||||
|
||||
</li>
|
||||
|
||||
<li class="md-nav__item">
|
||||
@@ -602,6 +611,15 @@
|
||||
</span>
|
||||
</a>
|
||||
|
||||
</li>
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="#database-configuration" class="md-nav__link">
|
||||
<span class="md-ellipsis">
|
||||
Database Configuration
|
||||
</span>
|
||||
</a>
|
||||
|
||||
</li>
|
||||
|
||||
<li class="md-nav__item">
|
||||
@@ -763,31 +781,38 @@
|
||||
<a id="__codelineno-1-34" name="__codelineno-1-34" href="#__codelineno-1-34"></a><span class="w"> </span><span class="nt">environment</span><span class="p">:</span><span class="w"> </span><span class="p p-Indicator">{}</span><span class="w"> </span><span class="c1"># Environment variables for the backend process</span>
|
||||
<a id="__codelineno-1-35" name="__codelineno-1-35" href="#__codelineno-1-35"></a><span class="w"> </span><span class="nt">response_headers</span><span class="p">:</span><span class="w"> </span><span class="p p-Indicator">{}</span><span class="w"> </span><span class="c1"># Additional response headers to send with responses</span>
|
||||
<a id="__codelineno-1-36" name="__codelineno-1-36" href="#__codelineno-1-36"></a>
|
||||
<a id="__codelineno-1-37" name="__codelineno-1-37" href="#__codelineno-1-37"></a><span class="nt">instances</span><span class="p">:</span>
|
||||
<a id="__codelineno-1-38" name="__codelineno-1-38" href="#__codelineno-1-38"></a><span class="w"> </span><span class="nt">port_range</span><span class="p">:</span><span class="w"> </span><span class="p p-Indicator">[</span><span class="nv">8000</span><span class="p p-Indicator">,</span><span class="w"> </span><span class="nv">9000</span><span class="p p-Indicator">]</span><span class="w"> </span><span class="c1"># Port range for instances</span>
|
||||
<a id="__codelineno-1-39" name="__codelineno-1-39" href="#__codelineno-1-39"></a><span class="w"> </span><span class="nt">data_dir</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">~/.local/share/llamactl</span><span class="w"> </span><span class="c1"># Data directory (platform-specific, see below)</span>
|
||||
<a id="__codelineno-1-40" name="__codelineno-1-40" href="#__codelineno-1-40"></a><span class="w"> </span><span class="nt">configs_dir</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">~/.local/share/llamactl/instances</span><span class="w"> </span><span class="c1"># Instance configs directory</span>
|
||||
<a id="__codelineno-1-41" name="__codelineno-1-41" href="#__codelineno-1-41"></a><span class="w"> </span><span class="nt">logs_dir</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">~/.local/share/llamactl/logs</span><span class="w"> </span><span class="c1"># Logs directory</span>
|
||||
<a id="__codelineno-1-42" name="__codelineno-1-42" href="#__codelineno-1-42"></a><span class="w"> </span><span class="nt">auto_create_dirs</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">true</span><span class="w"> </span><span class="c1"># Auto-create data/config/logs dirs if missing</span>
|
||||
<a id="__codelineno-1-43" name="__codelineno-1-43" href="#__codelineno-1-43"></a><span class="w"> </span><span class="nt">max_instances</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">-1</span><span class="w"> </span><span class="c1"># Max instances (-1 = unlimited)</span>
|
||||
<a id="__codelineno-1-44" name="__codelineno-1-44" href="#__codelineno-1-44"></a><span class="w"> </span><span class="nt">max_running_instances</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">-1</span><span class="w"> </span><span class="c1"># Max running instances (-1 = unlimited)</span>
|
||||
<a id="__codelineno-1-45" name="__codelineno-1-45" href="#__codelineno-1-45"></a><span class="w"> </span><span class="nt">enable_lru_eviction</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">true</span><span class="w"> </span><span class="c1"># Enable LRU eviction for idle instances</span>
|
||||
<a id="__codelineno-1-46" name="__codelineno-1-46" href="#__codelineno-1-46"></a><span class="w"> </span><span class="nt">default_auto_restart</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">true</span><span class="w"> </span><span class="c1"># Auto-restart new instances by default</span>
|
||||
<a id="__codelineno-1-47" name="__codelineno-1-47" href="#__codelineno-1-47"></a><span class="w"> </span><span class="nt">default_max_restarts</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">3</span><span class="w"> </span><span class="c1"># Max restarts for new instances</span>
|
||||
<a id="__codelineno-1-48" name="__codelineno-1-48" href="#__codelineno-1-48"></a><span class="w"> </span><span class="nt">default_restart_delay</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">5</span><span class="w"> </span><span class="c1"># Restart delay (seconds) for new instances</span>
|
||||
<a id="__codelineno-1-49" name="__codelineno-1-49" href="#__codelineno-1-49"></a><span class="w"> </span><span class="nt">default_on_demand_start</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">true</span><span class="w"> </span><span class="c1"># Default on-demand start setting</span>
|
||||
<a id="__codelineno-1-50" name="__codelineno-1-50" href="#__codelineno-1-50"></a><span class="w"> </span><span class="nt">on_demand_start_timeout</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">120</span><span class="w"> </span><span class="c1"># Default on-demand start timeout in seconds</span>
|
||||
<a id="__codelineno-1-51" name="__codelineno-1-51" href="#__codelineno-1-51"></a><span class="w"> </span><span class="nt">timeout_check_interval</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">5</span><span class="w"> </span><span class="c1"># Idle instance timeout check in minutes</span>
|
||||
<a id="__codelineno-1-52" name="__codelineno-1-52" href="#__codelineno-1-52"></a>
|
||||
<a id="__codelineno-1-53" name="__codelineno-1-53" href="#__codelineno-1-53"></a><span class="nt">auth</span><span class="p">:</span>
|
||||
<a id="__codelineno-1-54" name="__codelineno-1-54" href="#__codelineno-1-54"></a><span class="w"> </span><span class="nt">require_inference_auth</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">true</span><span class="w"> </span><span class="c1"># Require auth for inference endpoints</span>
|
||||
<a id="__codelineno-1-55" name="__codelineno-1-55" href="#__codelineno-1-55"></a><span class="w"> </span><span class="nt">inference_keys</span><span class="p">:</span><span class="w"> </span><span class="p p-Indicator">[]</span><span class="w"> </span><span class="c1"># Keys for inference endpoints</span>
|
||||
<a id="__codelineno-1-56" name="__codelineno-1-56" href="#__codelineno-1-56"></a><span class="w"> </span><span class="nt">require_management_auth</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">true</span><span class="w"> </span><span class="c1"># Require auth for management endpoints</span>
|
||||
<a id="__codelineno-1-57" name="__codelineno-1-57" href="#__codelineno-1-57"></a><span class="w"> </span><span class="nt">management_keys</span><span class="p">:</span><span class="w"> </span><span class="p p-Indicator">[]</span><span class="w"> </span><span class="c1"># Keys for management endpoints</span>
|
||||
<a id="__codelineno-1-58" name="__codelineno-1-58" href="#__codelineno-1-58"></a>
|
||||
<a id="__codelineno-1-59" name="__codelineno-1-59" href="#__codelineno-1-59"></a><span class="nt">local_node</span><span class="p">:</span><span class="w"> </span><span class="s">"main"</span><span class="w"> </span><span class="c1"># Name of the local node (default: "main")</span>
|
||||
<a id="__codelineno-1-60" name="__codelineno-1-60" href="#__codelineno-1-60"></a><span class="nt">nodes</span><span class="p">:</span><span class="w"> </span><span class="c1"># Node configuration for multi-node deployment</span>
|
||||
<a id="__codelineno-1-61" name="__codelineno-1-61" href="#__codelineno-1-61"></a><span class="w"> </span><span class="nt">main</span><span class="p">:</span><span class="w"> </span><span class="c1"># Default local node (empty config)</span>
|
||||
<a id="__codelineno-1-37" name="__codelineno-1-37" href="#__codelineno-1-37"></a><span class="nt">data_dir</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">~/.local/share/llamactl</span><span class="w"> </span><span class="c1"># Main data directory (database, instances, logs), default varies by OS</span>
|
||||
<a id="__codelineno-1-38" name="__codelineno-1-38" href="#__codelineno-1-38"></a>
|
||||
<a id="__codelineno-1-39" name="__codelineno-1-39" href="#__codelineno-1-39"></a><span class="nt">instances</span><span class="p">:</span>
|
||||
<a id="__codelineno-1-40" name="__codelineno-1-40" href="#__codelineno-1-40"></a><span class="w"> </span><span class="nt">port_range</span><span class="p">:</span><span class="w"> </span><span class="p p-Indicator">[</span><span class="nv">8000</span><span class="p p-Indicator">,</span><span class="w"> </span><span class="nv">9000</span><span class="p p-Indicator">]</span><span class="w"> </span><span class="c1"># Port range for instances</span>
|
||||
<a id="__codelineno-1-41" name="__codelineno-1-41" href="#__codelineno-1-41"></a><span class="w"> </span><span class="nt">configs_dir</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">data_dir/instances</span><span class="w"> </span><span class="c1"># Instance configs directory</span>
|
||||
<a id="__codelineno-1-42" name="__codelineno-1-42" href="#__codelineno-1-42"></a><span class="w"> </span><span class="nt">logs_dir</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">data_dir/logs</span><span class="w"> </span><span class="c1"># Logs directory</span>
|
||||
<a id="__codelineno-1-43" name="__codelineno-1-43" href="#__codelineno-1-43"></a><span class="w"> </span><span class="nt">auto_create_dirs</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">true</span><span class="w"> </span><span class="c1"># Auto-create data/config/logs dirs if missing</span>
|
||||
<a id="__codelineno-1-44" name="__codelineno-1-44" href="#__codelineno-1-44"></a><span class="w"> </span><span class="nt">max_instances</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">-1</span><span class="w"> </span><span class="c1"># Max instances (-1 = unlimited)</span>
|
||||
<a id="__codelineno-1-45" name="__codelineno-1-45" href="#__codelineno-1-45"></a><span class="w"> </span><span class="nt">max_running_instances</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">-1</span><span class="w"> </span><span class="c1"># Max running instances (-1 = unlimited)</span>
|
||||
<a id="__codelineno-1-46" name="__codelineno-1-46" href="#__codelineno-1-46"></a><span class="w"> </span><span class="nt">enable_lru_eviction</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">true</span><span class="w"> </span><span class="c1"># Enable LRU eviction for idle instances</span>
|
||||
<a id="__codelineno-1-47" name="__codelineno-1-47" href="#__codelineno-1-47"></a><span class="w"> </span><span class="nt">default_auto_restart</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">true</span><span class="w"> </span><span class="c1"># Auto-restart new instances by default</span>
|
||||
<a id="__codelineno-1-48" name="__codelineno-1-48" href="#__codelineno-1-48"></a><span class="w"> </span><span class="nt">default_max_restarts</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">3</span><span class="w"> </span><span class="c1"># Max restarts for new instances</span>
|
||||
<a id="__codelineno-1-49" name="__codelineno-1-49" href="#__codelineno-1-49"></a><span class="w"> </span><span class="nt">default_restart_delay</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">5</span><span class="w"> </span><span class="c1"># Restart delay (seconds) for new instances</span>
|
||||
<a id="__codelineno-1-50" name="__codelineno-1-50" href="#__codelineno-1-50"></a><span class="w"> </span><span class="nt">default_on_demand_start</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">true</span><span class="w"> </span><span class="c1"># Default on-demand start setting</span>
|
||||
<a id="__codelineno-1-51" name="__codelineno-1-51" href="#__codelineno-1-51"></a><span class="w"> </span><span class="nt">on_demand_start_timeout</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">120</span><span class="w"> </span><span class="c1"># Default on-demand start timeout in seconds</span>
|
||||
<a id="__codelineno-1-52" name="__codelineno-1-52" href="#__codelineno-1-52"></a><span class="w"> </span><span class="nt">timeout_check_interval</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">5</span><span class="w"> </span><span class="c1"># Idle instance timeout check in minutes</span>
|
||||
<a id="__codelineno-1-53" name="__codelineno-1-53" href="#__codelineno-1-53"></a>
|
||||
<a id="__codelineno-1-54" name="__codelineno-1-54" href="#__codelineno-1-54"></a><span class="nt">database</span><span class="p">:</span>
|
||||
<a id="__codelineno-1-55" name="__codelineno-1-55" href="#__codelineno-1-55"></a><span class="w"> </span><span class="nt">path</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">data_dir/llamactl.db</span><span class="w"> </span><span class="c1"># Database file path</span>
|
||||
<a id="__codelineno-1-56" name="__codelineno-1-56" href="#__codelineno-1-56"></a><span class="w"> </span><span class="nt">max_open_connections</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">25</span><span class="w"> </span><span class="c1"># Maximum open database connections</span>
|
||||
<a id="__codelineno-1-57" name="__codelineno-1-57" href="#__codelineno-1-57"></a><span class="w"> </span><span class="nt">max_idle_connections</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">5</span><span class="w"> </span><span class="c1"># Maximum idle database connections</span>
|
||||
<a id="__codelineno-1-58" name="__codelineno-1-58" href="#__codelineno-1-58"></a><span class="w"> </span><span class="nt">connection_max_lifetime</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">5m</span><span class="w"> </span><span class="c1"># Connection max lifetime</span>
|
||||
<a id="__codelineno-1-59" name="__codelineno-1-59" href="#__codelineno-1-59"></a>
|
||||
<a id="__codelineno-1-60" name="__codelineno-1-60" href="#__codelineno-1-60"></a><span class="nt">auth</span><span class="p">:</span>
|
||||
<a id="__codelineno-1-61" name="__codelineno-1-61" href="#__codelineno-1-61"></a><span class="w"> </span><span class="nt">require_inference_auth</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">true</span><span class="w"> </span><span class="c1"># Require auth for inference endpoints</span>
|
||||
<a id="__codelineno-1-62" name="__codelineno-1-62" href="#__codelineno-1-62"></a><span class="w"> </span><span class="nt">inference_keys</span><span class="p">:</span><span class="w"> </span><span class="p p-Indicator">[]</span><span class="w"> </span><span class="c1"># Keys for inference endpoints</span>
|
||||
<a id="__codelineno-1-63" name="__codelineno-1-63" href="#__codelineno-1-63"></a><span class="w"> </span><span class="nt">require_management_auth</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">true</span><span class="w"> </span><span class="c1"># Require auth for management endpoints</span>
|
||||
<a id="__codelineno-1-64" name="__codelineno-1-64" href="#__codelineno-1-64"></a><span class="w"> </span><span class="nt">management_keys</span><span class="p">:</span><span class="w"> </span><span class="p p-Indicator">[]</span><span class="w"> </span><span class="c1"># Keys for management endpoints</span>
|
||||
<a id="__codelineno-1-65" name="__codelineno-1-65" href="#__codelineno-1-65"></a>
|
||||
<a id="__codelineno-1-66" name="__codelineno-1-66" href="#__codelineno-1-66"></a><span class="nt">local_node</span><span class="p">:</span><span class="w"> </span><span class="s">"main"</span><span class="w"> </span><span class="c1"># Name of the local node (default: "main")</span>
|
||||
<a id="__codelineno-1-67" name="__codelineno-1-67" href="#__codelineno-1-67"></a><span class="nt">nodes</span><span class="p">:</span><span class="w"> </span><span class="c1"># Node configuration for multi-node deployment</span>
|
||||
<a id="__codelineno-1-68" name="__codelineno-1-68" href="#__codelineno-1-68"></a><span class="w"> </span><span class="nt">main</span><span class="p">:</span><span class="w"> </span><span class="c1"># Default local node (empty config)</span>
|
||||
</code></pre></div>
|
||||
<h2 id="configuration-files">Configuration Files<a class="headerlink" href="#configuration-files" title="Permanent link">¶</a></h2>
|
||||
<h3 id="configuration-file-locations">Configuration File Locations<a class="headerlink" href="#configuration-file-locations" title="Permanent link">¶</a></h3>
|
||||
@@ -888,26 +913,33 @@
|
||||
- <code>LLAMACTL_MLX_ARGS</code> - Space-separated default arguments<br />
|
||||
- <code>LLAMACTL_MLX_ENV</code> - Environment variables in format "KEY1=value1,KEY2=value2"<br />
|
||||
- <code>LLAMACTL_MLX_RESPONSE_HEADERS</code> - Response headers in format "KEY1=value1;KEY2=value2" </p>
|
||||
<h3 id="data-directory-configuration">Data Directory Configuration<a class="headerlink" href="#data-directory-configuration" title="Permanent link">¶</a></h3>
|
||||
<div class="highlight"><pre><span></span><code><a id="__codelineno-4-1" name="__codelineno-4-1" href="#__codelineno-4-1"></a><span class="nt">data_dir</span><span class="p">:</span><span class="w"> </span><span class="s">"~/.local/share/llamactl"</span><span class="w"> </span><span class="c1"># Main data directory for database, instances, and logs (default varies by OS)</span>
|
||||
</code></pre></div>
|
||||
<p><strong>Environment Variables:</strong><br />
|
||||
- <code>LLAMACTL_DATA_DIRECTORY</code> - Main data directory path </p>
|
||||
<p><strong>Default Data Directory by Platform:</strong><br />
|
||||
- <strong>Linux</strong>: <code>~/.local/share/llamactl</code><br />
|
||||
- <strong>macOS</strong>: <code>~/Library/Application Support/llamactl</code><br />
|
||||
- <strong>Windows</strong>: <code>%LOCALAPPDATA%\llamactl</code> or <code>%PROGRAMDATA%\llamactl</code> </p>
|
||||
<h3 id="instance-configuration">Instance Configuration<a class="headerlink" href="#instance-configuration" title="Permanent link">¶</a></h3>
|
||||
<div class="highlight"><pre><span></span><code><a id="__codelineno-4-1" name="__codelineno-4-1" href="#__codelineno-4-1"></a><span class="nt">instances</span><span class="p">:</span>
|
||||
<a id="__codelineno-4-2" name="__codelineno-4-2" href="#__codelineno-4-2"></a><span class="w"> </span><span class="nt">port_range</span><span class="p">:</span><span class="w"> </span><span class="p p-Indicator">[</span><span class="nv">8000</span><span class="p p-Indicator">,</span><span class="w"> </span><span class="nv">9000</span><span class="p p-Indicator">]</span><span class="w"> </span><span class="c1"># Port range for instances (default: [8000, 9000])</span>
|
||||
<a id="__codelineno-4-3" name="__codelineno-4-3" href="#__codelineno-4-3"></a><span class="w"> </span><span class="nt">data_dir</span><span class="p">:</span><span class="w"> </span><span class="s">"~/.local/share/llamactl"</span><span class="w"> </span><span class="c1"># Directory for all llamactl data (default varies by OS)</span>
|
||||
<a id="__codelineno-4-4" name="__codelineno-4-4" href="#__codelineno-4-4"></a><span class="w"> </span><span class="nt">configs_dir</span><span class="p">:</span><span class="w"> </span><span class="s">"~/.local/share/llamactl/instances"</span><span class="w"> </span><span class="c1"># Directory for instance configs (default: data_dir/instances)</span>
|
||||
<a id="__codelineno-4-5" name="__codelineno-4-5" href="#__codelineno-4-5"></a><span class="w"> </span><span class="nt">logs_dir</span><span class="p">:</span><span class="w"> </span><span class="s">"~/.local/share/llamactl/logs"</span><span class="w"> </span><span class="c1"># Directory for instance logs (default: data_dir/logs)</span>
|
||||
<a id="__codelineno-4-6" name="__codelineno-4-6" href="#__codelineno-4-6"></a><span class="w"> </span><span class="nt">auto_create_dirs</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">true</span><span class="w"> </span><span class="c1"># Automatically create data/config/logs directories (default: true)</span>
|
||||
<a id="__codelineno-4-7" name="__codelineno-4-7" href="#__codelineno-4-7"></a><span class="w"> </span><span class="nt">max_instances</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">-1</span><span class="w"> </span><span class="c1"># Maximum instances (-1 = unlimited)</span>
|
||||
<a id="__codelineno-4-8" name="__codelineno-4-8" href="#__codelineno-4-8"></a><span class="w"> </span><span class="nt">max_running_instances</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">-1</span><span class="w"> </span><span class="c1"># Maximum running instances (-1 = unlimited)</span>
|
||||
<a id="__codelineno-4-9" name="__codelineno-4-9" href="#__codelineno-4-9"></a><span class="w"> </span><span class="nt">enable_lru_eviction</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">true</span><span class="w"> </span><span class="c1"># Enable LRU eviction for idle instances</span>
|
||||
<a id="__codelineno-4-10" name="__codelineno-4-10" href="#__codelineno-4-10"></a><span class="w"> </span><span class="nt">default_auto_restart</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">true</span><span class="w"> </span><span class="c1"># Default auto-restart setting</span>
|
||||
<a id="__codelineno-4-11" name="__codelineno-4-11" href="#__codelineno-4-11"></a><span class="w"> </span><span class="nt">default_max_restarts</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">3</span><span class="w"> </span><span class="c1"># Default maximum restart attempts</span>
|
||||
<a id="__codelineno-4-12" name="__codelineno-4-12" href="#__codelineno-4-12"></a><span class="w"> </span><span class="nt">default_restart_delay</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">5</span><span class="w"> </span><span class="c1"># Default restart delay in seconds</span>
|
||||
<a id="__codelineno-4-13" name="__codelineno-4-13" href="#__codelineno-4-13"></a><span class="w"> </span><span class="nt">default_on_demand_start</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">true</span><span class="w"> </span><span class="c1"># Default on-demand start setting</span>
|
||||
<a id="__codelineno-4-14" name="__codelineno-4-14" href="#__codelineno-4-14"></a><span class="w"> </span><span class="nt">on_demand_start_timeout</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">120</span><span class="w"> </span><span class="c1"># Default on-demand start timeout in seconds</span>
|
||||
<a id="__codelineno-4-15" name="__codelineno-4-15" href="#__codelineno-4-15"></a><span class="w"> </span><span class="nt">timeout_check_interval</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">5</span><span class="w"> </span><span class="c1"># Default instance timeout check interval in minutes</span>
|
||||
<div class="highlight"><pre><span></span><code><a id="__codelineno-5-1" name="__codelineno-5-1" href="#__codelineno-5-1"></a><span class="nt">instances</span><span class="p">:</span>
|
||||
<a id="__codelineno-5-2" name="__codelineno-5-2" href="#__codelineno-5-2"></a><span class="w"> </span><span class="nt">port_range</span><span class="p">:</span><span class="w"> </span><span class="p p-Indicator">[</span><span class="nv">8000</span><span class="p p-Indicator">,</span><span class="w"> </span><span class="nv">9000</span><span class="p p-Indicator">]</span><span class="w"> </span><span class="c1"># Port range for instances (default: [8000, 9000])</span>
|
||||
<a id="__codelineno-5-3" name="__codelineno-5-3" href="#__codelineno-5-3"></a><span class="w"> </span><span class="nt">configs_dir</span><span class="p">:</span><span class="w"> </span><span class="s">"instances"</span><span class="w"> </span><span class="c1"># Directory for instance configs, default: data_dir/instances</span>
|
||||
<a id="__codelineno-5-4" name="__codelineno-5-4" href="#__codelineno-5-4"></a><span class="w"> </span><span class="nt">logs_dir</span><span class="p">:</span><span class="w"> </span><span class="s">"logs"</span><span class="w"> </span><span class="c1"># Directory for instance logs, default: data_dir/logs</span>
|
||||
<a id="__codelineno-5-5" name="__codelineno-5-5" href="#__codelineno-5-5"></a><span class="w"> </span><span class="nt">auto_create_dirs</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">true</span><span class="w"> </span><span class="c1"># Automatically create data/config/logs directories (default: true)</span>
|
||||
<a id="__codelineno-5-6" name="__codelineno-5-6" href="#__codelineno-5-6"></a><span class="w"> </span><span class="nt">max_instances</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">-1</span><span class="w"> </span><span class="c1"># Maximum instances (-1 = unlimited)</span>
|
||||
<a id="__codelineno-5-7" name="__codelineno-5-7" href="#__codelineno-5-7"></a><span class="w"> </span><span class="nt">max_running_instances</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">-1</span><span class="w"> </span><span class="c1"># Maximum running instances (-1 = unlimited)</span>
|
||||
<a id="__codelineno-5-8" name="__codelineno-5-8" href="#__codelineno-5-8"></a><span class="w"> </span><span class="nt">enable_lru_eviction</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">true</span><span class="w"> </span><span class="c1"># Enable LRU eviction for idle instances</span>
|
||||
<a id="__codelineno-5-9" name="__codelineno-5-9" href="#__codelineno-5-9"></a><span class="w"> </span><span class="nt">default_auto_restart</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">true</span><span class="w"> </span><span class="c1"># Default auto-restart setting</span>
|
||||
<a id="__codelineno-5-10" name="__codelineno-5-10" href="#__codelineno-5-10"></a><span class="w"> </span><span class="nt">default_max_restarts</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">3</span><span class="w"> </span><span class="c1"># Default maximum restart attempts</span>
|
||||
<a id="__codelineno-5-11" name="__codelineno-5-11" href="#__codelineno-5-11"></a><span class="w"> </span><span class="nt">default_restart_delay</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">5</span><span class="w"> </span><span class="c1"># Default restart delay in seconds</span>
|
||||
<a id="__codelineno-5-12" name="__codelineno-5-12" href="#__codelineno-5-12"></a><span class="w"> </span><span class="nt">default_on_demand_start</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">true</span><span class="w"> </span><span class="c1"># Default on-demand start setting</span>
|
||||
<a id="__codelineno-5-13" name="__codelineno-5-13" href="#__codelineno-5-13"></a><span class="w"> </span><span class="nt">on_demand_start_timeout</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">120</span><span class="w"> </span><span class="c1"># Default on-demand start timeout in seconds</span>
|
||||
<a id="__codelineno-5-14" name="__codelineno-5-14" href="#__codelineno-5-14"></a><span class="w"> </span><span class="nt">timeout_check_interval</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">5</span><span class="w"> </span><span class="c1"># Default instance timeout check interval in minutes</span>
|
||||
</code></pre></div>
|
||||
<p><strong>Environment Variables:</strong><br />
|
||||
- <code>LLAMACTL_INSTANCE_PORT_RANGE</code> - Port range (format: "8000-9000" or "8000,9000")<br />
|
||||
- <code>LLAMACTL_DATA_DIRECTORY</code> - Data directory path<br />
|
||||
- <code>LLAMACTL_INSTANCES_DIR</code> - Instance configs directory path<br />
|
||||
- <code>LLAMACTL_LOGS_DIR</code> - Log directory path<br />
|
||||
- <code>LLAMACTL_AUTO_CREATE_DATA_DIR</code> - Auto-create data/config/logs directories (true/false)<br />
|
||||
@@ -920,12 +952,24 @@
|
||||
- <code>LLAMACTL_DEFAULT_ON_DEMAND_START</code> - Default on-demand start setting (true/false)<br />
|
||||
- <code>LLAMACTL_ON_DEMAND_START_TIMEOUT</code> - Default on-demand start timeout in seconds<br />
|
||||
- <code>LLAMACTL_TIMEOUT_CHECK_INTERVAL</code> - Default instance timeout check interval in minutes </p>
|
||||
<h3 id="database-configuration">Database Configuration<a class="headerlink" href="#database-configuration" title="Permanent link">¶</a></h3>
|
||||
<div class="highlight"><pre><span></span><code><a id="__codelineno-6-1" name="__codelineno-6-1" href="#__codelineno-6-1"></a><span class="nt">database</span><span class="p">:</span>
|
||||
<a id="__codelineno-6-2" name="__codelineno-6-2" href="#__codelineno-6-2"></a><span class="w"> </span><span class="nt">path</span><span class="p">:</span><span class="w"> </span><span class="s">"llamactl.db"</span><span class="w"> </span><span class="c1"># Database file path, default: data_dir/llamactl.db</span>
|
||||
<a id="__codelineno-6-3" name="__codelineno-6-3" href="#__codelineno-6-3"></a><span class="w"> </span><span class="nt">max_open_connections</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">25</span><span class="w"> </span><span class="c1"># Maximum open database connections (default: 25)</span>
|
||||
<a id="__codelineno-6-4" name="__codelineno-6-4" href="#__codelineno-6-4"></a><span class="w"> </span><span class="nt">max_idle_connections</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">5</span><span class="w"> </span><span class="c1"># Maximum idle database connections (default: 5)</span>
|
||||
<a id="__codelineno-6-5" name="__codelineno-6-5" href="#__codelineno-6-5"></a><span class="w"> </span><span class="nt">connection_max_lifetime</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">5m</span><span class="w"> </span><span class="c1"># Connection max lifetime (default: 5m)</span>
|
||||
</code></pre></div>
|
||||
<p><strong>Environment Variables:</strong><br />
|
||||
- <code>LLAMACTL_DATABASE_PATH</code> - Database file path (relative to data_dir or absolute)<br />
|
||||
- <code>LLAMACTL_DATABASE_MAX_OPEN_CONNECTIONS</code> - Maximum open database connections<br />
|
||||
- <code>LLAMACTL_DATABASE_MAX_IDLE_CONNECTIONS</code> - Maximum idle database connections<br />
|
||||
- <code>LLAMACTL_DATABASE_CONN_MAX_LIFETIME</code> - Connection max lifetime (e.g., "5m", "1h") </p>
|
||||
<h3 id="authentication-configuration">Authentication Configuration<a class="headerlink" href="#authentication-configuration" title="Permanent link">¶</a></h3>
|
||||
<div class="highlight"><pre><span></span><code><a id="__codelineno-5-1" name="__codelineno-5-1" href="#__codelineno-5-1"></a><span class="nt">auth</span><span class="p">:</span>
|
||||
<a id="__codelineno-5-2" name="__codelineno-5-2" href="#__codelineno-5-2"></a><span class="w"> </span><span class="nt">require_inference_auth</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">true</span><span class="w"> </span><span class="c1"># Require API key for OpenAI endpoints (default: true)</span>
|
||||
<a id="__codelineno-5-3" name="__codelineno-5-3" href="#__codelineno-5-3"></a><span class="w"> </span><span class="nt">inference_keys</span><span class="p">:</span><span class="w"> </span><span class="p p-Indicator">[]</span><span class="w"> </span><span class="c1"># List of valid inference API keys</span>
|
||||
<a id="__codelineno-5-4" name="__codelineno-5-4" href="#__codelineno-5-4"></a><span class="w"> </span><span class="nt">require_management_auth</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">true</span><span class="w"> </span><span class="c1"># Require API key for management endpoints (default: true)</span>
|
||||
<a id="__codelineno-5-5" name="__codelineno-5-5" href="#__codelineno-5-5"></a><span class="w"> </span><span class="nt">management_keys</span><span class="p">:</span><span class="w"> </span><span class="p p-Indicator">[]</span><span class="w"> </span><span class="c1"># List of valid management API keys</span>
|
||||
<div class="highlight"><pre><span></span><code><a id="__codelineno-7-1" name="__codelineno-7-1" href="#__codelineno-7-1"></a><span class="nt">auth</span><span class="p">:</span>
|
||||
<a id="__codelineno-7-2" name="__codelineno-7-2" href="#__codelineno-7-2"></a><span class="w"> </span><span class="nt">require_inference_auth</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">true</span><span class="w"> </span><span class="c1"># Require API key for OpenAI endpoints (default: true)</span>
|
||||
<a id="__codelineno-7-3" name="__codelineno-7-3" href="#__codelineno-7-3"></a><span class="w"> </span><span class="nt">inference_keys</span><span class="p">:</span><span class="w"> </span><span class="p p-Indicator">[]</span><span class="w"> </span><span class="c1"># List of valid inference API keys</span>
|
||||
<a id="__codelineno-7-4" name="__codelineno-7-4" href="#__codelineno-7-4"></a><span class="w"> </span><span class="nt">require_management_auth</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">true</span><span class="w"> </span><span class="c1"># Require API key for management endpoints (default: true)</span>
|
||||
<a id="__codelineno-7-5" name="__codelineno-7-5" href="#__codelineno-7-5"></a><span class="w"> </span><span class="nt">management_keys</span><span class="p">:</span><span class="w"> </span><span class="p p-Indicator">[]</span><span class="w"> </span><span class="c1"># List of valid management API keys</span>
|
||||
</code></pre></div>
|
||||
<p><strong>Environment Variables:</strong><br />
|
||||
- <code>LLAMACTL_REQUIRE_INFERENCE_AUTH</code> - Require auth for OpenAI endpoints (true/false)<br />
|
||||
@@ -934,14 +978,14 @@
|
||||
- <code>LLAMACTL_MANAGEMENT_KEYS</code> - Comma-separated management API keys </p>
|
||||
<h3 id="remote-node-configuration">Remote Node Configuration<a class="headerlink" href="#remote-node-configuration" title="Permanent link">¶</a></h3>
|
||||
<p>llamactl supports remote node deployments. Configure remote nodes to deploy instances on remote hosts and manage them centrally. </p>
|
||||
<div class="highlight"><pre><span></span><code><a id="__codelineno-6-1" name="__codelineno-6-1" href="#__codelineno-6-1"></a><span class="nt">local_node</span><span class="p">:</span><span class="w"> </span><span class="s">"main"</span><span class="w"> </span><span class="c1"># Name of the local node (default: "main")</span>
|
||||
<a id="__codelineno-6-2" name="__codelineno-6-2" href="#__codelineno-6-2"></a><span class="nt">nodes</span><span class="p">:</span><span class="w"> </span><span class="c1"># Node configuration map</span>
|
||||
<a id="__codelineno-6-3" name="__codelineno-6-3" href="#__codelineno-6-3"></a><span class="w"> </span><span class="nt">main</span><span class="p">:</span><span class="w"> </span><span class="c1"># Local node (empty address means local)</span>
|
||||
<a id="__codelineno-6-4" name="__codelineno-6-4" href="#__codelineno-6-4"></a><span class="w"> </span><span class="nt">address</span><span class="p">:</span><span class="w"> </span><span class="s">""</span><span class="w"> </span><span class="c1"># Not used for local node</span>
|
||||
<a id="__codelineno-6-5" name="__codelineno-6-5" href="#__codelineno-6-5"></a><span class="w"> </span><span class="nt">api_key</span><span class="p">:</span><span class="w"> </span><span class="s">""</span><span class="w"> </span><span class="c1"># Not used for local node</span>
|
||||
<a id="__codelineno-6-6" name="__codelineno-6-6" href="#__codelineno-6-6"></a><span class="w"> </span><span class="nt">worker1</span><span class="p">:</span><span class="w"> </span><span class="c1"># Remote worker node</span>
|
||||
<a id="__codelineno-6-7" name="__codelineno-6-7" href="#__codelineno-6-7"></a><span class="w"> </span><span class="nt">address</span><span class="p">:</span><span class="w"> </span><span class="s">"http://192.168.1.10:8080"</span>
|
||||
<a id="__codelineno-6-8" name="__codelineno-6-8" href="#__codelineno-6-8"></a><span class="w"> </span><span class="nt">api_key</span><span class="p">:</span><span class="w"> </span><span class="s">"worker1-api-key"</span><span class="w"> </span><span class="c1"># Management API key for authentication</span>
|
||||
<div class="highlight"><pre><span></span><code><a id="__codelineno-8-1" name="__codelineno-8-1" href="#__codelineno-8-1"></a><span class="nt">local_node</span><span class="p">:</span><span class="w"> </span><span class="s">"main"</span><span class="w"> </span><span class="c1"># Name of the local node (default: "main")</span>
|
||||
<a id="__codelineno-8-2" name="__codelineno-8-2" href="#__codelineno-8-2"></a><span class="nt">nodes</span><span class="p">:</span><span class="w"> </span><span class="c1"># Node configuration map</span>
|
||||
<a id="__codelineno-8-3" name="__codelineno-8-3" href="#__codelineno-8-3"></a><span class="w"> </span><span class="nt">main</span><span class="p">:</span><span class="w"> </span><span class="c1"># Local node (empty address means local)</span>
|
||||
<a id="__codelineno-8-4" name="__codelineno-8-4" href="#__codelineno-8-4"></a><span class="w"> </span><span class="nt">address</span><span class="p">:</span><span class="w"> </span><span class="s">""</span><span class="w"> </span><span class="c1"># Not used for local node</span>
|
||||
<a id="__codelineno-8-5" name="__codelineno-8-5" href="#__codelineno-8-5"></a><span class="w"> </span><span class="nt">api_key</span><span class="p">:</span><span class="w"> </span><span class="s">""</span><span class="w"> </span><span class="c1"># Not used for local node</span>
|
||||
<a id="__codelineno-8-6" name="__codelineno-8-6" href="#__codelineno-8-6"></a><span class="w"> </span><span class="nt">worker1</span><span class="p">:</span><span class="w"> </span><span class="c1"># Remote worker node</span>
|
||||
<a id="__codelineno-8-7" name="__codelineno-8-7" href="#__codelineno-8-7"></a><span class="w"> </span><span class="nt">address</span><span class="p">:</span><span class="w"> </span><span class="s">"http://192.168.1.10:8080"</span>
|
||||
<a id="__codelineno-8-8" name="__codelineno-8-8" href="#__codelineno-8-8"></a><span class="w"> </span><span class="nt">api_key</span><span class="p">:</span><span class="w"> </span><span class="s">"worker1-api-key"</span><span class="w"> </span><span class="c1"># Management API key for authentication</span>
|
||||
</code></pre></div>
|
||||
<p><strong>Node Configuration Fields:</strong><br />
|
||||
- <code>local_node</code>: Specifies which node in the <code>nodes</code> map represents the local node. Must match exactly what other nodes call this node.<br />
|
||||
@@ -970,7 +1014,7 @@
|
||||
<span class="md-icon" title="Last update">
|
||||
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M21 13.1c-.1 0-.3.1-.4.2l-1 1 2.1 2.1 1-1c.2-.2.2-.6 0-.8l-1.3-1.3c-.1-.1-.2-.2-.4-.2m-1.9 1.8-6.1 6V23h2.1l6.1-6.1zM12.5 7v5.2l4 2.4-1 1L11 13V7zM11 21.9c-5.1-.5-9-4.8-9-9.9C2 6.5 6.5 2 12 2c5.3 0 9.6 4.1 10 9.3-.3-.1-.6-.2-1-.2s-.7.1-1 .2C19.6 7.2 16.2 4 12 4c-4.4 0-8 3.6-8 8 0 4.1 3.1 7.5 7.1 7.9l-.1.2z"/></svg>
|
||||
</span>
|
||||
<span class="git-revision-date-localized-plugin git-revision-date-localized-plugin-date" title="October 26, 2025 16:19:53 UTC">October 26, 2025</span>
|
||||
<span class="git-revision-date-localized-plugin git-revision-date-localized-plugin-date" title="December 2, 2025 19:07:39 UTC">December 2, 2025</span>
|
||||
</span>
|
||||
|
||||
|
||||
|
||||
File diff suppressed because one or more lines are too long
Reference in New Issue
Block a user