mirror of
https://github.com/lordmathis/llamactl.git
synced 2025-11-06 09:04:27 +00:00
Deployed ebc82c3 to dev with MkDocs 1.5.3 and mike 2.0.0
This commit is contained in:
@@ -856,6 +856,72 @@
|
||||
</ul>
|
||||
</nav>
|
||||
|
||||
</li>
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="#backend-specific-endpoints" class="md-nav__link">
|
||||
<span class="md-ellipsis">
|
||||
Backend-Specific Endpoints
|
||||
</span>
|
||||
</a>
|
||||
|
||||
<nav class="md-nav" aria-label="Backend-Specific Endpoints">
|
||||
<ul class="md-nav__list">
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="#parse-commands" class="md-nav__link">
|
||||
<span class="md-ellipsis">
|
||||
Parse Commands
|
||||
</span>
|
||||
</a>
|
||||
|
||||
<nav class="md-nav" aria-label="Parse Commands">
|
||||
<ul class="md-nav__list">
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="#parse-llamacpp-command" class="md-nav__link">
|
||||
<span class="md-ellipsis">
|
||||
Parse Llama.cpp Command
|
||||
</span>
|
||||
</a>
|
||||
|
||||
</li>
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="#parse-mlx-lm-command" class="md-nav__link">
|
||||
<span class="md-ellipsis">
|
||||
Parse MLX-LM Command
|
||||
</span>
|
||||
</a>
|
||||
|
||||
</li>
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="#parse-vllm-command" class="md-nav__link">
|
||||
<span class="md-ellipsis">
|
||||
Parse vLLM Command
|
||||
</span>
|
||||
</a>
|
||||
|
||||
</li>
|
||||
|
||||
</ul>
|
||||
</nav>
|
||||
|
||||
</li>
|
||||
|
||||
</ul>
|
||||
</nav>
|
||||
|
||||
</li>
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="#auto-generated-documentation" class="md-nav__link">
|
||||
<span class="md-ellipsis">
|
||||
Auto-Generated Documentation
|
||||
</span>
|
||||
</a>
|
||||
|
||||
</li>
|
||||
|
||||
<li class="md-nav__item">
|
||||
@@ -1216,6 +1282,72 @@
|
||||
</ul>
|
||||
</nav>
|
||||
|
||||
</li>
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="#backend-specific-endpoints" class="md-nav__link">
|
||||
<span class="md-ellipsis">
|
||||
Backend-Specific Endpoints
|
||||
</span>
|
||||
</a>
|
||||
|
||||
<nav class="md-nav" aria-label="Backend-Specific Endpoints">
|
||||
<ul class="md-nav__list">
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="#parse-commands" class="md-nav__link">
|
||||
<span class="md-ellipsis">
|
||||
Parse Commands
|
||||
</span>
|
||||
</a>
|
||||
|
||||
<nav class="md-nav" aria-label="Parse Commands">
|
||||
<ul class="md-nav__list">
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="#parse-llamacpp-command" class="md-nav__link">
|
||||
<span class="md-ellipsis">
|
||||
Parse Llama.cpp Command
|
||||
</span>
|
||||
</a>
|
||||
|
||||
</li>
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="#parse-mlx-lm-command" class="md-nav__link">
|
||||
<span class="md-ellipsis">
|
||||
Parse MLX-LM Command
|
||||
</span>
|
||||
</a>
|
||||
|
||||
</li>
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="#parse-vllm-command" class="md-nav__link">
|
||||
<span class="md-ellipsis">
|
||||
Parse vLLM Command
|
||||
</span>
|
||||
</a>
|
||||
|
||||
</li>
|
||||
|
||||
</ul>
|
||||
</nav>
|
||||
|
||||
</li>
|
||||
|
||||
</ul>
|
||||
</nav>
|
||||
|
||||
</li>
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="#auto-generated-documentation" class="md-nav__link">
|
||||
<span class="md-ellipsis">
|
||||
Auto-Generated Documentation
|
||||
</span>
|
||||
</a>
|
||||
|
||||
</li>
|
||||
|
||||
<li class="md-nav__item">
|
||||
@@ -1346,7 +1478,7 @@
|
||||
<p><strong>Response:</strong>
|
||||
<div class="highlight"><pre><span></span><code><a id="__codelineno-17-1" name="__codelineno-17-1" href="#__codelineno-17-1"></a><span class="p">{</span>
|
||||
<a id="__codelineno-17-2" name="__codelineno-17-2" href="#__codelineno-17-2"></a><span class="w"> </span><span class="nt">"name"</span><span class="p">:</span><span class="w"> </span><span class="s2">"llama2-7b"</span><span class="p">,</span>
|
||||
<a id="__codelineno-17-3" name="__codelineno-17-3" href="#__codelineno-17-3"></a><span class="w"> </span><span class="nt">"status"</span><span class="p">:</span><span class="w"> </span><span class="s2">"starting"</span><span class="p">,</span>
|
||||
<a id="__codelineno-17-3" name="__codelineno-17-3" href="#__codelineno-17-3"></a><span class="w"> </span><span class="nt">"status"</span><span class="p">:</span><span class="w"> </span><span class="s2">"running"</span><span class="p">,</span>
|
||||
<a id="__codelineno-17-4" name="__codelineno-17-4" href="#__codelineno-17-4"></a><span class="w"> </span><span class="nt">"created"</span><span class="p">:</span><span class="w"> </span><span class="mi">1705312200</span>
|
||||
<a id="__codelineno-17-5" name="__codelineno-17-5" href="#__codelineno-17-5"></a><span class="p">}</span>
|
||||
</code></pre></div></p>
|
||||
@@ -1360,7 +1492,7 @@
|
||||
<p><strong>Response:</strong>
|
||||
<div class="highlight"><pre><span></span><code><a id="__codelineno-19-1" name="__codelineno-19-1" href="#__codelineno-19-1"></a><span class="p">{</span>
|
||||
<a id="__codelineno-19-2" name="__codelineno-19-2" href="#__codelineno-19-2"></a><span class="w"> </span><span class="nt">"name"</span><span class="p">:</span><span class="w"> </span><span class="s2">"llama2-7b"</span><span class="p">,</span>
|
||||
<a id="__codelineno-19-3" name="__codelineno-19-3" href="#__codelineno-19-3"></a><span class="w"> </span><span class="nt">"status"</span><span class="p">:</span><span class="w"> </span><span class="s2">"stopping"</span><span class="p">,</span>
|
||||
<a id="__codelineno-19-3" name="__codelineno-19-3" href="#__codelineno-19-3"></a><span class="w"> </span><span class="nt">"status"</span><span class="p">:</span><span class="w"> </span><span class="s2">"stopped"</span><span class="p">,</span>
|
||||
<a id="__codelineno-19-4" name="__codelineno-19-4" href="#__codelineno-19-4"></a><span class="w"> </span><span class="nt">"created"</span><span class="p">:</span><span class="w"> </span><span class="mi">1705312200</span>
|
||||
<a id="__codelineno-19-5" name="__codelineno-19-5" href="#__codelineno-19-5"></a><span class="p">}</span>
|
||||
</code></pre></div></p>
|
||||
@@ -1371,7 +1503,7 @@
|
||||
<p><strong>Response:</strong>
|
||||
<div class="highlight"><pre><span></span><code><a id="__codelineno-21-1" name="__codelineno-21-1" href="#__codelineno-21-1"></a><span class="p">{</span>
|
||||
<a id="__codelineno-21-2" name="__codelineno-21-2" href="#__codelineno-21-2"></a><span class="w"> </span><span class="nt">"name"</span><span class="p">:</span><span class="w"> </span><span class="s2">"llama2-7b"</span><span class="p">,</span>
|
||||
<a id="__codelineno-21-3" name="__codelineno-21-3" href="#__codelineno-21-3"></a><span class="w"> </span><span class="nt">"status"</span><span class="p">:</span><span class="w"> </span><span class="s2">"restarting"</span><span class="p">,</span>
|
||||
<a id="__codelineno-21-3" name="__codelineno-21-3" href="#__codelineno-21-3"></a><span class="w"> </span><span class="nt">"status"</span><span class="p">:</span><span class="w"> </span><span class="s2">"running"</span><span class="p">,</span>
|
||||
<a id="__codelineno-21-4" name="__codelineno-21-4" href="#__codelineno-21-4"></a><span class="w"> </span><span class="nt">"created"</span><span class="p">:</span><span class="w"> </span><span class="mi">1705312200</span>
|
||||
<a id="__codelineno-21-5" name="__codelineno-21-5" href="#__codelineno-21-5"></a><span class="p">}</span>
|
||||
</code></pre></div></p>
|
||||
@@ -1443,9 +1575,9 @@
|
||||
- <code>503 Service Unavailable</code>: Instance is not running and on-demand start is disabled
|
||||
- <code>409 Conflict</code>: Cannot start instance due to maximum instances limit</p>
|
||||
<h2 id="instance-status-values">Instance Status Values<a class="headerlink" href="#instance-status-values" title="Permanent link">¶</a></h2>
|
||||
<p>Instances can have the following status values:<br />
|
||||
- <code>stopped</code>: Instance is not running<br />
|
||||
- <code>running</code>: Instance is running and ready to accept requests<br />
|
||||
<p>Instances can have the following status values:
|
||||
- <code>stopped</code>: Instance is not running
|
||||
- <code>running</code>: Instance is running and ready to accept requests
|
||||
- <code>failed</code>: Instance failed to start or crashed </p>
|
||||
<h2 id="error-responses">Error Responses<a class="headerlink" href="#error-responses" title="Permanent link">¶</a></h2>
|
||||
<p>All endpoints may return error responses in the following format:</p>
|
||||
@@ -1515,9 +1647,76 @@
|
||||
<a id="__codelineno-32-7" name="__codelineno-32-7" href="#__codelineno-32-7"></a><span class="s1"> "n_predict": 50</span>
|
||||
<a id="__codelineno-32-8" name="__codelineno-32-8" href="#__codelineno-32-8"></a><span class="s1"> }'</span>
|
||||
</code></pre></div>
|
||||
<h2 id="backend-specific-endpoints">Backend-Specific Endpoints<a class="headerlink" href="#backend-specific-endpoints" title="Permanent link">¶</a></h2>
|
||||
<h3 id="parse-commands">Parse Commands<a class="headerlink" href="#parse-commands" title="Permanent link">¶</a></h3>
|
||||
<p>Llamactl provides endpoints to parse command strings from different backends into instance configuration options.</p>
|
||||
<h4 id="parse-llamacpp-command">Parse Llama.cpp Command<a class="headerlink" href="#parse-llamacpp-command" title="Permanent link">¶</a></h4>
|
||||
<p>Parse a llama-server command string into instance options.</p>
|
||||
<div class="highlight"><pre><span></span><code><a id="__codelineno-33-1" name="__codelineno-33-1" href="#__codelineno-33-1"></a><span class="err">POST /api/v1/backends/llama-cpp/parse-command</span>
|
||||
</code></pre></div>
|
||||
<p><strong>Request Body:</strong>
|
||||
<div class="highlight"><pre><span></span><code><a id="__codelineno-34-1" name="__codelineno-34-1" href="#__codelineno-34-1"></a><span class="p">{</span>
|
||||
<a id="__codelineno-34-2" name="__codelineno-34-2" href="#__codelineno-34-2"></a><span class="w"> </span><span class="nt">"command"</span><span class="p">:</span><span class="w"> </span><span class="s2">"llama-server -m /path/to/model.gguf -c 2048 --port 8080"</span>
|
||||
<a id="__codelineno-34-3" name="__codelineno-34-3" href="#__codelineno-34-3"></a><span class="p">}</span>
|
||||
</code></pre></div></p>
|
||||
<p><strong>Response:</strong>
|
||||
<div class="highlight"><pre><span></span><code><a id="__codelineno-35-1" name="__codelineno-35-1" href="#__codelineno-35-1"></a><span class="p">{</span>
|
||||
<a id="__codelineno-35-2" name="__codelineno-35-2" href="#__codelineno-35-2"></a><span class="w"> </span><span class="nt">"backend_type"</span><span class="p">:</span><span class="w"> </span><span class="s2">"llama_cpp"</span><span class="p">,</span>
|
||||
<a id="__codelineno-35-3" name="__codelineno-35-3" href="#__codelineno-35-3"></a><span class="w"> </span><span class="nt">"llama_server_options"</span><span class="p">:</span><span class="w"> </span><span class="p">{</span>
|
||||
<a id="__codelineno-35-4" name="__codelineno-35-4" href="#__codelineno-35-4"></a><span class="w"> </span><span class="nt">"model"</span><span class="p">:</span><span class="w"> </span><span class="s2">"/path/to/model.gguf"</span><span class="p">,</span>
|
||||
<a id="__codelineno-35-5" name="__codelineno-35-5" href="#__codelineno-35-5"></a><span class="w"> </span><span class="nt">"ctx_size"</span><span class="p">:</span><span class="w"> </span><span class="mi">2048</span><span class="p">,</span>
|
||||
<a id="__codelineno-35-6" name="__codelineno-35-6" href="#__codelineno-35-6"></a><span class="w"> </span><span class="nt">"port"</span><span class="p">:</span><span class="w"> </span><span class="mi">8080</span>
|
||||
<a id="__codelineno-35-7" name="__codelineno-35-7" href="#__codelineno-35-7"></a><span class="w"> </span><span class="p">}</span>
|
||||
<a id="__codelineno-35-8" name="__codelineno-35-8" href="#__codelineno-35-8"></a><span class="p">}</span>
|
||||
</code></pre></div></p>
|
||||
<h4 id="parse-mlx-lm-command">Parse MLX-LM Command<a class="headerlink" href="#parse-mlx-lm-command" title="Permanent link">¶</a></h4>
|
||||
<p>Parse an MLX-LM server command string into instance options.</p>
|
||||
<div class="highlight"><pre><span></span><code><a id="__codelineno-36-1" name="__codelineno-36-1" href="#__codelineno-36-1"></a><span class="err">POST /api/v1/backends/mlx/parse-command</span>
|
||||
</code></pre></div>
|
||||
<p><strong>Request Body:</strong>
|
||||
<div class="highlight"><pre><span></span><code><a id="__codelineno-37-1" name="__codelineno-37-1" href="#__codelineno-37-1"></a><span class="p">{</span>
|
||||
<a id="__codelineno-37-2" name="__codelineno-37-2" href="#__codelineno-37-2"></a><span class="w"> </span><span class="nt">"command"</span><span class="p">:</span><span class="w"> </span><span class="s2">"mlx_lm.server --model /path/to/model --port 8080"</span>
|
||||
<a id="__codelineno-37-3" name="__codelineno-37-3" href="#__codelineno-37-3"></a><span class="p">}</span>
|
||||
</code></pre></div></p>
|
||||
<p><strong>Response:</strong>
|
||||
<div class="highlight"><pre><span></span><code><a id="__codelineno-38-1" name="__codelineno-38-1" href="#__codelineno-38-1"></a><span class="p">{</span>
|
||||
<a id="__codelineno-38-2" name="__codelineno-38-2" href="#__codelineno-38-2"></a><span class="w"> </span><span class="nt">"backend_type"</span><span class="p">:</span><span class="w"> </span><span class="s2">"mlx_lm"</span><span class="p">,</span>
|
||||
<a id="__codelineno-38-3" name="__codelineno-38-3" href="#__codelineno-38-3"></a><span class="w"> </span><span class="nt">"mlx_server_options"</span><span class="p">:</span><span class="w"> </span><span class="p">{</span>
|
||||
<a id="__codelineno-38-4" name="__codelineno-38-4" href="#__codelineno-38-4"></a><span class="w"> </span><span class="nt">"model"</span><span class="p">:</span><span class="w"> </span><span class="s2">"/path/to/model"</span><span class="p">,</span>
|
||||
<a id="__codelineno-38-5" name="__codelineno-38-5" href="#__codelineno-38-5"></a><span class="w"> </span><span class="nt">"port"</span><span class="p">:</span><span class="w"> </span><span class="mi">8080</span>
|
||||
<a id="__codelineno-38-6" name="__codelineno-38-6" href="#__codelineno-38-6"></a><span class="w"> </span><span class="p">}</span>
|
||||
<a id="__codelineno-38-7" name="__codelineno-38-7" href="#__codelineno-38-7"></a><span class="p">}</span>
|
||||
</code></pre></div></p>
|
||||
<h4 id="parse-vllm-command">Parse vLLM Command<a class="headerlink" href="#parse-vllm-command" title="Permanent link">¶</a></h4>
|
||||
<p>Parse a vLLM serve command string into instance options.</p>
|
||||
<div class="highlight"><pre><span></span><code><a id="__codelineno-39-1" name="__codelineno-39-1" href="#__codelineno-39-1"></a><span class="err">POST /api/v1/backends/vllm/parse-command</span>
|
||||
</code></pre></div>
|
||||
<p><strong>Request Body:</strong>
|
||||
<div class="highlight"><pre><span></span><code><a id="__codelineno-40-1" name="__codelineno-40-1" href="#__codelineno-40-1"></a><span class="p">{</span>
|
||||
<a id="__codelineno-40-2" name="__codelineno-40-2" href="#__codelineno-40-2"></a><span class="w"> </span><span class="nt">"command"</span><span class="p">:</span><span class="w"> </span><span class="s2">"vllm serve /path/to/model --port 8080"</span>
|
||||
<a id="__codelineno-40-3" name="__codelineno-40-3" href="#__codelineno-40-3"></a><span class="p">}</span>
|
||||
</code></pre></div></p>
|
||||
<p><strong>Response:</strong>
|
||||
<div class="highlight"><pre><span></span><code><a id="__codelineno-41-1" name="__codelineno-41-1" href="#__codelineno-41-1"></a><span class="p">{</span>
|
||||
<a id="__codelineno-41-2" name="__codelineno-41-2" href="#__codelineno-41-2"></a><span class="w"> </span><span class="nt">"backend_type"</span><span class="p">:</span><span class="w"> </span><span class="s2">"vllm"</span><span class="p">,</span>
|
||||
<a id="__codelineno-41-3" name="__codelineno-41-3" href="#__codelineno-41-3"></a><span class="w"> </span><span class="nt">"vllm_server_options"</span><span class="p">:</span><span class="w"> </span><span class="p">{</span>
|
||||
<a id="__codelineno-41-4" name="__codelineno-41-4" href="#__codelineno-41-4"></a><span class="w"> </span><span class="nt">"model"</span><span class="p">:</span><span class="w"> </span><span class="s2">"/path/to/model"</span><span class="p">,</span>
|
||||
<a id="__codelineno-41-5" name="__codelineno-41-5" href="#__codelineno-41-5"></a><span class="w"> </span><span class="nt">"port"</span><span class="p">:</span><span class="w"> </span><span class="mi">8080</span>
|
||||
<a id="__codelineno-41-6" name="__codelineno-41-6" href="#__codelineno-41-6"></a><span class="w"> </span><span class="p">}</span>
|
||||
<a id="__codelineno-41-7" name="__codelineno-41-7" href="#__codelineno-41-7"></a><span class="p">}</span>
|
||||
</code></pre></div></p>
|
||||
<p><strong>Error Responses for Parse Commands:</strong>
|
||||
- <code>400 Bad Request</code>: Invalid request body, empty command, or parse error
|
||||
- <code>500 Internal Server Error</code>: Encoding error</p>
|
||||
<h2 id="auto-generated-documentation">Auto-Generated Documentation<a class="headerlink" href="#auto-generated-documentation" title="Permanent link">¶</a></h2>
|
||||
<p>The API documentation is automatically generated from code annotations using Swagger/OpenAPI. To regenerate the documentation:</p>
|
||||
<ol>
|
||||
<li>Install the swag tool: <code>go install github.com/swaggo/swag/cmd/swag@latest</code></li>
|
||||
<li>Generate docs: <code>swag init -g cmd/server/main.go -o apidocs</code></li>
|
||||
</ol>
|
||||
<h2 id="swagger-documentation">Swagger Documentation<a class="headerlink" href="#swagger-documentation" title="Permanent link">¶</a></h2>
|
||||
<p>If swagger documentation is enabled in the server configuration, you can access the interactive API documentation at:</p>
|
||||
<div class="highlight"><pre><span></span><code><a id="__codelineno-33-1" name="__codelineno-33-1" href="#__codelineno-33-1"></a>http://localhost:8080/swagger/
|
||||
<div class="highlight"><pre><span></span><code><a id="__codelineno-42-1" name="__codelineno-42-1" href="#__codelineno-42-1"></a>http://localhost:8080/swagger/
|
||||
</code></pre></div>
|
||||
<p>This provides a complete interactive interface for testing all API endpoints.</p>
|
||||
|
||||
@@ -1540,7 +1739,7 @@
|
||||
<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 6V23h2.1l6.1-6.1-2.1-2M12.5 7v5.2l4 2.4-1 1L11 13V7h1.5M11 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-.1.2v1.8Z"/></svg>
|
||||
</span>
|
||||
<span class="git-revision-date-localized-plugin git-revision-date-localized-plugin-date">September 3, 2025</span>
|
||||
<span class="git-revision-date-localized-plugin git-revision-date-localized-plugin-date">September 21, 2025</span>
|
||||
</span>
|
||||
|
||||
|
||||
|
||||
Reference in New Issue
Block a user