mirror of
https://github.com/lordmathis/llamactl.git
synced 2025-11-06 00:54:23 +00:00
Deployed a824f06 to dev with MkDocs 1.5.3 and mike 2.0.0
This commit is contained in:
lordmathis
@@ -851,31 +851,49 @@
|
||||
<a id="__codelineno-1-5" name="__codelineno-1-5" href="#__codelineno-1-5"></a><span class="w"> </span><span class="nt">enable_swagger</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">false</span><span class="w"> </span><span class="c1"># Enable Swagger UI for API docs</span>
|
||||
<a id="__codelineno-1-6" name="__codelineno-1-6" href="#__codelineno-1-6"></a>
|
||||
<a id="__codelineno-1-7" name="__codelineno-1-7" href="#__codelineno-1-7"></a><span class="nt">backends</span><span class="p">:</span>
|
||||
<a id="__codelineno-1-8" name="__codelineno-1-8" href="#__codelineno-1-8"></a><span class="w"> </span><span class="nt">llama_executable</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">llama-server</span><span class="w"> </span><span class="c1"># Path to llama-server executable</span>
|
||||
<a id="__codelineno-1-9" name="__codelineno-1-9" href="#__codelineno-1-9"></a><span class="w"> </span><span class="nt">mlx_lm_executable</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">mlx_lm.server</span><span class="w"> </span><span class="c1"># Path to mlx_lm.server executable</span>
|
||||
<a id="__codelineno-1-10" name="__codelineno-1-10" href="#__codelineno-1-10"></a><span class="w"> </span><span class="nt">vllm_executable</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">vllm</span><span class="w"> </span><span class="c1"># Path to vllm executable</span>
|
||||
<a id="__codelineno-1-11" name="__codelineno-1-11" href="#__codelineno-1-11"></a>
|
||||
<a id="__codelineno-1-12" name="__codelineno-1-12" href="#__codelineno-1-12"></a><span class="nt">instances</span><span class="p">:</span>
|
||||
<a id="__codelineno-1-13" name="__codelineno-1-13" href="#__codelineno-1-13"></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-1-14" name="__codelineno-1-14" href="#__codelineno-1-14"></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-1-15" name="__codelineno-1-15" href="#__codelineno-1-15"></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-1-16" name="__codelineno-1-16" href="#__codelineno-1-16"></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-1-17" name="__codelineno-1-17" href="#__codelineno-1-17"></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-1-18" name="__codelineno-1-18" href="#__codelineno-1-18"></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-1-19" name="__codelineno-1-19" href="#__codelineno-1-19"></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-1-20" name="__codelineno-1-20" href="#__codelineno-1-20"></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-1-21" name="__codelineno-1-21" href="#__codelineno-1-21"></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-1-22" name="__codelineno-1-22" href="#__codelineno-1-22"></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-1-23" name="__codelineno-1-23" href="#__codelineno-1-23"></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-1-24" name="__codelineno-1-24" href="#__codelineno-1-24"></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-1-25" name="__codelineno-1-25" href="#__codelineno-1-25"></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-1-26" name="__codelineno-1-26" href="#__codelineno-1-26"></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-1-27" name="__codelineno-1-27" href="#__codelineno-1-27"></a>
|
||||
<a id="__codelineno-1-28" name="__codelineno-1-28" href="#__codelineno-1-28"></a><span class="nt">auth</span><span class="p">:</span>
|
||||
<a id="__codelineno-1-29" name="__codelineno-1-29" href="#__codelineno-1-29"></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-1-30" name="__codelineno-1-30" href="#__codelineno-1-30"></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-1-31" name="__codelineno-1-31" href="#__codelineno-1-31"></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-1-32" name="__codelineno-1-32" href="#__codelineno-1-32"></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-1-8" name="__codelineno-1-8" href="#__codelineno-1-8"></a><span class="w"> </span><span class="nt">llama-cpp</span><span class="p">:</span>
|
||||
<a id="__codelineno-1-9" name="__codelineno-1-9" href="#__codelineno-1-9"></a><span class="w"> </span><span class="nt">command</span><span class="p">:</span><span class="w"> </span><span class="s">"llama-server"</span>
|
||||
<a id="__codelineno-1-10" name="__codelineno-1-10" href="#__codelineno-1-10"></a><span class="w"> </span><span class="nt">args</span><span class="p">:</span><span class="w"> </span><span class="p p-Indicator">[]</span>
|
||||
<a id="__codelineno-1-11" name="__codelineno-1-11" href="#__codelineno-1-11"></a><span class="w"> </span><span class="nt">docker</span><span class="p">:</span>
|
||||
<a id="__codelineno-1-12" name="__codelineno-1-12" href="#__codelineno-1-12"></a><span class="w"> </span><span class="nt">enabled</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">false</span>
|
||||
<a id="__codelineno-1-13" name="__codelineno-1-13" href="#__codelineno-1-13"></a><span class="w"> </span><span class="nt">image</span><span class="p">:</span><span class="w"> </span><span class="s">"ghcr.io/ggml-org/llama.cpp:server"</span>
|
||||
<a id="__codelineno-1-14" name="__codelineno-1-14" href="#__codelineno-1-14"></a><span class="w"> </span><span class="nt">args</span><span class="p">:</span><span class="w"> </span><span class="p p-Indicator">[</span><span class="s">"run"</span><span class="p p-Indicator">,</span><span class="w"> </span><span class="s">"--rm"</span><span class="p p-Indicator">,</span><span class="w"> </span><span class="s">"--network"</span><span class="p p-Indicator">,</span><span class="w"> </span><span class="s">"host"</span><span class="p p-Indicator">,</span><span class="w"> </span><span class="s">"--gpus"</span><span class="p p-Indicator">,</span><span class="w"> </span><span class="s">"all"</span><span class="p p-Indicator">]</span>
|
||||
<a id="__codelineno-1-15" name="__codelineno-1-15" href="#__codelineno-1-15"></a><span class="w"> </span><span class="nt">environment</span><span class="p">:</span><span class="w"> </span><span class="p p-Indicator">{}</span>
|
||||
<a id="__codelineno-1-16" name="__codelineno-1-16" href="#__codelineno-1-16"></a>
|
||||
<a id="__codelineno-1-17" name="__codelineno-1-17" href="#__codelineno-1-17"></a><span class="w"> </span><span class="nt">vllm</span><span class="p">:</span>
|
||||
<a id="__codelineno-1-18" name="__codelineno-1-18" href="#__codelineno-1-18"></a><span class="w"> </span><span class="nt">command</span><span class="p">:</span><span class="w"> </span><span class="s">"vllm"</span>
|
||||
<a id="__codelineno-1-19" name="__codelineno-1-19" href="#__codelineno-1-19"></a><span class="w"> </span><span class="nt">args</span><span class="p">:</span><span class="w"> </span><span class="p p-Indicator">[</span><span class="s">"serve"</span><span class="p p-Indicator">]</span>
|
||||
<a id="__codelineno-1-20" name="__codelineno-1-20" href="#__codelineno-1-20"></a><span class="w"> </span><span class="nt">docker</span><span class="p">:</span>
|
||||
<a id="__codelineno-1-21" name="__codelineno-1-21" href="#__codelineno-1-21"></a><span class="w"> </span><span class="nt">enabled</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">false</span>
|
||||
<a id="__codelineno-1-22" name="__codelineno-1-22" href="#__codelineno-1-22"></a><span class="w"> </span><span class="nt">image</span><span class="p">:</span><span class="w"> </span><span class="s">"vllm/vllm-openai:latest"</span>
|
||||
<a id="__codelineno-1-23" name="__codelineno-1-23" href="#__codelineno-1-23"></a><span class="w"> </span><span class="nt">args</span><span class="p">:</span><span class="w"> </span><span class="p p-Indicator">[</span><span class="s">"run"</span><span class="p p-Indicator">,</span><span class="w"> </span><span class="s">"--rm"</span><span class="p p-Indicator">,</span><span class="w"> </span><span class="s">"--network"</span><span class="p p-Indicator">,</span><span class="w"> </span><span class="s">"host"</span><span class="p p-Indicator">,</span><span class="w"> </span><span class="s">"--gpus"</span><span class="p p-Indicator">,</span><span class="w"> </span><span class="s">"all"</span><span class="p p-Indicator">,</span><span class="w"> </span><span class="s">"--shm-size"</span><span class="p p-Indicator">,</span><span class="w"> </span><span class="s">"1g"</span><span class="p p-Indicator">]</span>
|
||||
<a id="__codelineno-1-24" name="__codelineno-1-24" href="#__codelineno-1-24"></a><span class="w"> </span><span class="nt">environment</span><span class="p">:</span><span class="w"> </span><span class="p p-Indicator">{}</span>
|
||||
<a id="__codelineno-1-25" name="__codelineno-1-25" href="#__codelineno-1-25"></a>
|
||||
<a id="__codelineno-1-26" name="__codelineno-1-26" href="#__codelineno-1-26"></a><span class="w"> </span><span class="nt">mlx</span><span class="p">:</span>
|
||||
<a id="__codelineno-1-27" name="__codelineno-1-27" href="#__codelineno-1-27"></a><span class="w"> </span><span class="nt">command</span><span class="p">:</span><span class="w"> </span><span class="s">"mlx_lm.server"</span>
|
||||
<a id="__codelineno-1-28" name="__codelineno-1-28" href="#__codelineno-1-28"></a><span class="w"> </span><span class="nt">args</span><span class="p">:</span><span class="w"> </span><span class="p p-Indicator">[]</span>
|
||||
<a id="__codelineno-1-29" name="__codelineno-1-29" href="#__codelineno-1-29"></a>
|
||||
<a id="__codelineno-1-30" name="__codelineno-1-30" href="#__codelineno-1-30"></a><span class="nt">instances</span><span class="p">:</span>
|
||||
<a id="__codelineno-1-31" name="__codelineno-1-31" href="#__codelineno-1-31"></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-1-32" name="__codelineno-1-32" href="#__codelineno-1-32"></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-1-33" name="__codelineno-1-33" href="#__codelineno-1-33"></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-1-34" name="__codelineno-1-34" href="#__codelineno-1-34"></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-1-35" name="__codelineno-1-35" href="#__codelineno-1-35"></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-1-36" name="__codelineno-1-36" href="#__codelineno-1-36"></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-1-37" name="__codelineno-1-37" href="#__codelineno-1-37"></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-1-38" name="__codelineno-1-38" href="#__codelineno-1-38"></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-1-39" name="__codelineno-1-39" href="#__codelineno-1-39"></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-1-40" name="__codelineno-1-40" href="#__codelineno-1-40"></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-1-41" name="__codelineno-1-41" href="#__codelineno-1-41"></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-1-42" name="__codelineno-1-42" href="#__codelineno-1-42"></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-1-43" name="__codelineno-1-43" href="#__codelineno-1-43"></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-1-44" name="__codelineno-1-44" href="#__codelineno-1-44"></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-1-45" name="__codelineno-1-45" href="#__codelineno-1-45"></a>
|
||||
<a id="__codelineno-1-46" name="__codelineno-1-46" href="#__codelineno-1-46"></a><span class="nt">auth</span><span class="p">:</span>
|
||||
<a id="__codelineno-1-47" name="__codelineno-1-47" href="#__codelineno-1-47"></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-1-48" name="__codelineno-1-48" href="#__codelineno-1-48"></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-1-49" name="__codelineno-1-49" href="#__codelineno-1-49"></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-1-50" name="__codelineno-1-50" href="#__codelineno-1-50"></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>
|
||||
</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>
|
||||
@@ -909,14 +927,37 @@
|
||||
- <code>LLAMACTL_ENABLE_SWAGGER</code> - Enable Swagger UI (true/false)</p>
|
||||
<h3 id="backend-configuration">Backend Configuration<a class="headerlink" href="#backend-configuration" title="Permanent link">¶</a></h3>
|
||||
<div class="highlight"><pre><span></span><code><a id="__codelineno-3-1" name="__codelineno-3-1" href="#__codelineno-3-1"></a><span class="nt">backends</span><span class="p">:</span>
|
||||
<a id="__codelineno-3-2" name="__codelineno-3-2" href="#__codelineno-3-2"></a><span class="w"> </span><span class="nt">llama_executable</span><span class="p">:</span><span class="w"> </span><span class="s">"llama-server"</span><span class="w"> </span><span class="c1"># Path to llama-server executable (default: "llama-server")</span>
|
||||
<a id="__codelineno-3-3" name="__codelineno-3-3" href="#__codelineno-3-3"></a><span class="w"> </span><span class="nt">mlx_lm_executable</span><span class="p">:</span><span class="w"> </span><span class="s">"mlx_lm.server"</span><span class="w"> </span><span class="c1"># Path to mlx_lm.server executable (default: "mlx_lm.server")</span>
|
||||
<a id="__codelineno-3-4" name="__codelineno-3-4" href="#__codelineno-3-4"></a><span class="w"> </span><span class="nt">vllm_executable</span><span class="p">:</span><span class="w"> </span><span class="s">"vllm"</span><span class="w"> </span><span class="c1"># Path to vllm executable (default: "vllm")</span>
|
||||
<a id="__codelineno-3-2" name="__codelineno-3-2" href="#__codelineno-3-2"></a><span class="w"> </span><span class="nt">llama-cpp</span><span class="p">:</span>
|
||||
<a id="__codelineno-3-3" name="__codelineno-3-3" href="#__codelineno-3-3"></a><span class="w"> </span><span class="nt">command</span><span class="p">:</span><span class="w"> </span><span class="s">"llama-server"</span>
|
||||
<a id="__codelineno-3-4" name="__codelineno-3-4" href="#__codelineno-3-4"></a><span class="w"> </span><span class="nt">args</span><span class="p">:</span><span class="w"> </span><span class="p p-Indicator">[]</span>
|
||||
<a id="__codelineno-3-5" name="__codelineno-3-5" href="#__codelineno-3-5"></a><span class="w"> </span><span class="nt">docker</span><span class="p">:</span>
|
||||
<a id="__codelineno-3-6" name="__codelineno-3-6" href="#__codelineno-3-6"></a><span class="w"> </span><span class="nt">enabled</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">false</span><span class="w"> </span><span class="c1"># Enable Docker runtime (default: false)</span>
|
||||
<a id="__codelineno-3-7" name="__codelineno-3-7" href="#__codelineno-3-7"></a><span class="w"> </span><span class="nt">image</span><span class="p">:</span><span class="w"> </span><span class="s">"ghcr.io/ggml-org/llama.cpp:server"</span>
|
||||
<a id="__codelineno-3-8" name="__codelineno-3-8" href="#__codelineno-3-8"></a><span class="w"> </span><span class="nt">args</span><span class="p">:</span><span class="w"> </span><span class="p p-Indicator">[</span><span class="s">"run"</span><span class="p p-Indicator">,</span><span class="w"> </span><span class="s">"--rm"</span><span class="p p-Indicator">,</span><span class="w"> </span><span class="s">"--network"</span><span class="p p-Indicator">,</span><span class="w"> </span><span class="s">"host"</span><span class="p p-Indicator">,</span><span class="w"> </span><span class="s">"--gpus"</span><span class="p p-Indicator">,</span><span class="w"> </span><span class="s">"all"</span><span class="p p-Indicator">]</span>
|
||||
<a id="__codelineno-3-9" name="__codelineno-3-9" href="#__codelineno-3-9"></a><span class="w"> </span><span class="nt">environment</span><span class="p">:</span><span class="w"> </span><span class="p p-Indicator">{}</span>
|
||||
<a id="__codelineno-3-10" name="__codelineno-3-10" href="#__codelineno-3-10"></a>
|
||||
<a id="__codelineno-3-11" name="__codelineno-3-11" href="#__codelineno-3-11"></a><span class="w"> </span><span class="nt">vllm</span><span class="p">:</span>
|
||||
<a id="__codelineno-3-12" name="__codelineno-3-12" href="#__codelineno-3-12"></a><span class="w"> </span><span class="nt">command</span><span class="p">:</span><span class="w"> </span><span class="s">"vllm"</span>
|
||||
<a id="__codelineno-3-13" name="__codelineno-3-13" href="#__codelineno-3-13"></a><span class="w"> </span><span class="nt">args</span><span class="p">:</span><span class="w"> </span><span class="p p-Indicator">[</span><span class="s">"serve"</span><span class="p p-Indicator">]</span>
|
||||
<a id="__codelineno-3-14" name="__codelineno-3-14" href="#__codelineno-3-14"></a><span class="w"> </span><span class="nt">docker</span><span class="p">:</span>
|
||||
<a id="__codelineno-3-15" name="__codelineno-3-15" href="#__codelineno-3-15"></a><span class="w"> </span><span class="nt">enabled</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">false</span>
|
||||
<a id="__codelineno-3-16" name="__codelineno-3-16" href="#__codelineno-3-16"></a><span class="w"> </span><span class="nt">image</span><span class="p">:</span><span class="w"> </span><span class="s">"vllm/vllm-openai:latest"</span>
|
||||
<a id="__codelineno-3-17" name="__codelineno-3-17" href="#__codelineno-3-17"></a><span class="w"> </span><span class="nt">args</span><span class="p">:</span><span class="w"> </span><span class="p p-Indicator">[</span><span class="s">"run"</span><span class="p p-Indicator">,</span><span class="w"> </span><span class="s">"--rm"</span><span class="p p-Indicator">,</span><span class="w"> </span><span class="s">"--network"</span><span class="p p-Indicator">,</span><span class="w"> </span><span class="s">"host"</span><span class="p p-Indicator">,</span><span class="w"> </span><span class="s">"--gpus"</span><span class="p p-Indicator">,</span><span class="w"> </span><span class="s">"all"</span><span class="p p-Indicator">,</span><span class="w"> </span><span class="s">"--shm-size"</span><span class="p p-Indicator">,</span><span class="w"> </span><span class="s">"1g"</span><span class="p p-Indicator">]</span>
|
||||
<a id="__codelineno-3-18" name="__codelineno-3-18" href="#__codelineno-3-18"></a><span class="w"> </span><span class="nt">environment</span><span class="p">:</span><span class="w"> </span><span class="p p-Indicator">{}</span>
|
||||
<a id="__codelineno-3-19" name="__codelineno-3-19" href="#__codelineno-3-19"></a>
|
||||
<a id="__codelineno-3-20" name="__codelineno-3-20" href="#__codelineno-3-20"></a><span class="w"> </span><span class="nt">mlx</span><span class="p">:</span>
|
||||
<a id="__codelineno-3-21" name="__codelineno-3-21" href="#__codelineno-3-21"></a><span class="w"> </span><span class="nt">command</span><span class="p">:</span><span class="w"> </span><span class="s">"mlx_lm.server"</span>
|
||||
<a id="__codelineno-3-22" name="__codelineno-3-22" href="#__codelineno-3-22"></a><span class="w"> </span><span class="nt">args</span><span class="p">:</span><span class="w"> </span><span class="p p-Indicator">[]</span>
|
||||
<a id="__codelineno-3-23" name="__codelineno-3-23" href="#__codelineno-3-23"></a><span class="w"> </span><span class="c1"># MLX does not support Docker</span>
|
||||
</code></pre></div>
|
||||
<p><strong>Environment Variables:</strong>
|
||||
- <code>LLAMACTL_LLAMA_EXECUTABLE</code> - Path to llama-server executable
|
||||
- <code>LLAMACTL_MLX_LM_EXECUTABLE</code> - Path to mlx_lm.server executable
|
||||
- <code>LLAMACTL_VLLM_EXECUTABLE</code> - Path to vllm executable</p>
|
||||
<p><strong>Backend Configuration Fields:</strong>
|
||||
- <code>command</code>: Executable name/path for the backend
|
||||
- <code>args</code>: Default arguments prepended to all instances
|
||||
- <code>docker</code>: Docker-specific configuration (optional)
|
||||
- <code>enabled</code>: Boolean flag to enable Docker runtime
|
||||
- <code>image</code>: Docker image to use
|
||||
- <code>args</code>: Additional arguments passed to <code>docker run</code>
|
||||
- <code>environment</code>: Environment variables for the container (optional)</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>
|
||||
@@ -986,7 +1027,7 @@
|
||||
<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 21, 2025</span>
|
||||
<span class="git-revision-date-localized-plugin git-revision-date-localized-plugin-date">September 24, 2025</span>
|
||||
</span>
|
||||
|
||||
|
||||
|
||||
@@ -501,6 +501,15 @@
|
||||
</span>
|
||||
</a>
|
||||
|
||||
</li>
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="#docker-support" class="md-nav__link">
|
||||
<span class="md-ellipsis">
|
||||
Docker Support
|
||||
</span>
|
||||
</a>
|
||||
|
||||
</li>
|
||||
|
||||
<li class="md-nav__item">
|
||||
@@ -781,6 +790,15 @@
|
||||
</span>
|
||||
</a>
|
||||
|
||||
</li>
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="#docker-support" class="md-nav__link">
|
||||
<span class="md-ellipsis">
|
||||
Docker Support
|
||||
</span>
|
||||
</a>
|
||||
|
||||
</li>
|
||||
|
||||
<li class="md-nav__item">
|
||||
@@ -932,67 +950,78 @@
|
||||
<a id="__codelineno-4-8" name="__codelineno-4-8" href="#__codelineno-4-8"></a><span class="w"> </span><span class="p">}</span>
|
||||
<a id="__codelineno-4-9" name="__codelineno-4-9" href="#__codelineno-4-9"></a><span class="p">}</span>
|
||||
</code></pre></div></p>
|
||||
<h2 id="docker-support">Docker Support<a class="headerlink" href="#docker-support" title="Permanent link">¶</a></h2>
|
||||
<p>Llamactl can run backends in Docker containers. To enable Docker for a backend, add a <code>docker</code> section to that backend in your YAML configuration file (e.g. <code>config.yaml</code>) as shown below:</p>
|
||||
<div class="highlight"><pre><span></span><code><a id="__codelineno-5-1" name="__codelineno-5-1" href="#__codelineno-5-1"></a><span class="nt">backends</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">vllm</span><span class="p">:</span>
|
||||
<a id="__codelineno-5-3" name="__codelineno-5-3" href="#__codelineno-5-3"></a><span class="w"> </span><span class="nt">command</span><span class="p">:</span><span class="w"> </span><span class="s">"vllm"</span>
|
||||
<a id="__codelineno-5-4" name="__codelineno-5-4" href="#__codelineno-5-4"></a><span class="w"> </span><span class="nt">args</span><span class="p">:</span><span class="w"> </span><span class="p p-Indicator">[</span><span class="s">"serve"</span><span class="p p-Indicator">]</span>
|
||||
<a id="__codelineno-5-5" name="__codelineno-5-5" href="#__codelineno-5-5"></a><span class="w"> </span><span class="nt">docker</span><span class="p">:</span>
|
||||
<a id="__codelineno-5-6" name="__codelineno-5-6" href="#__codelineno-5-6"></a><span class="w"> </span><span class="nt">enabled</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">true</span>
|
||||
<a id="__codelineno-5-7" name="__codelineno-5-7" href="#__codelineno-5-7"></a><span class="w"> </span><span class="nt">image</span><span class="p">:</span><span class="w"> </span><span class="s">"vllm/vllm-openai:latest"</span>
|
||||
<a id="__codelineno-5-8" name="__codelineno-5-8" href="#__codelineno-5-8"></a><span class="w"> </span><span class="nt">args</span><span class="p">:</span><span class="w"> </span><span class="p p-Indicator">[</span><span class="s">"run"</span><span class="p p-Indicator">,</span><span class="w"> </span><span class="s">"--rm"</span><span class="p p-Indicator">,</span><span class="w"> </span><span class="s">"--network"</span><span class="p p-Indicator">,</span><span class="w"> </span><span class="s">"host"</span><span class="p p-Indicator">,</span><span class="w"> </span><span class="s">"--gpus"</span><span class="p p-Indicator">,</span><span class="w"> </span><span class="s">"all"</span><span class="p p-Indicator">,</span><span class="w"> </span><span class="s">"--shm-size"</span><span class="p p-Indicator">,</span><span class="w"> </span><span class="s">"1g"</span><span class="p p-Indicator">]</span>
|
||||
</code></pre></div>
|
||||
<h2 id="using-the-api">Using the API<a class="headerlink" href="#using-the-api" title="Permanent link">¶</a></h2>
|
||||
<p>You can also manage instances via the REST API:</p>
|
||||
<div class="highlight"><pre><span></span><code><a id="__codelineno-5-1" name="__codelineno-5-1" href="#__codelineno-5-1"></a><span class="c1"># List all instances</span>
|
||||
<a id="__codelineno-5-2" name="__codelineno-5-2" href="#__codelineno-5-2"></a>curl<span class="w"> </span>http://localhost:8080/api/instances
|
||||
<a id="__codelineno-5-3" name="__codelineno-5-3" href="#__codelineno-5-3"></a>
|
||||
<a id="__codelineno-5-4" name="__codelineno-5-4" href="#__codelineno-5-4"></a><span class="c1"># Create a new llama.cpp instance</span>
|
||||
<a id="__codelineno-5-5" name="__codelineno-5-5" href="#__codelineno-5-5"></a>curl<span class="w"> </span>-X<span class="w"> </span>POST<span class="w"> </span>http://localhost:8080/api/instances/my-model<span class="w"> </span><span class="se">\</span>
|
||||
<a id="__codelineno-5-6" name="__codelineno-5-6" href="#__codelineno-5-6"></a><span class="w"> </span>-H<span class="w"> </span><span class="s2">"Content-Type: application/json"</span><span class="w"> </span><span class="se">\</span>
|
||||
<a id="__codelineno-5-7" name="__codelineno-5-7" href="#__codelineno-5-7"></a><span class="w"> </span>-d<span class="w"> </span><span class="s1">'{</span>
|
||||
<a id="__codelineno-5-8" name="__codelineno-5-8" href="#__codelineno-5-8"></a><span class="s1"> "backend_type": "llama_cpp",</span>
|
||||
<a id="__codelineno-5-9" name="__codelineno-5-9" href="#__codelineno-5-9"></a><span class="s1"> "backend_options": {</span>
|
||||
<a id="__codelineno-5-10" name="__codelineno-5-10" href="#__codelineno-5-10"></a><span class="s1"> "model": "/path/to/model.gguf"</span>
|
||||
<a id="__codelineno-5-11" name="__codelineno-5-11" href="#__codelineno-5-11"></a><span class="s1"> }</span>
|
||||
<a id="__codelineno-5-12" name="__codelineno-5-12" href="#__codelineno-5-12"></a><span class="s1"> }'</span>
|
||||
<a id="__codelineno-5-13" name="__codelineno-5-13" href="#__codelineno-5-13"></a>
|
||||
<a id="__codelineno-5-14" name="__codelineno-5-14" href="#__codelineno-5-14"></a><span class="c1"># Start an instance</span>
|
||||
<a id="__codelineno-5-15" name="__codelineno-5-15" href="#__codelineno-5-15"></a>curl<span class="w"> </span>-X<span class="w"> </span>POST<span class="w"> </span>http://localhost:8080/api/instances/my-model/start
|
||||
<div class="highlight"><pre><span></span><code><a id="__codelineno-6-1" name="__codelineno-6-1" href="#__codelineno-6-1"></a><span class="c1"># List all instances</span>
|
||||
<a id="__codelineno-6-2" name="__codelineno-6-2" href="#__codelineno-6-2"></a>curl<span class="w"> </span>http://localhost:8080/api/instances
|
||||
<a id="__codelineno-6-3" name="__codelineno-6-3" href="#__codelineno-6-3"></a>
|
||||
<a id="__codelineno-6-4" name="__codelineno-6-4" href="#__codelineno-6-4"></a><span class="c1"># Create a new llama.cpp instance</span>
|
||||
<a id="__codelineno-6-5" name="__codelineno-6-5" href="#__codelineno-6-5"></a>curl<span class="w"> </span>-X<span class="w"> </span>POST<span class="w"> </span>http://localhost:8080/api/instances/my-model<span class="w"> </span><span class="se">\</span>
|
||||
<a id="__codelineno-6-6" name="__codelineno-6-6" href="#__codelineno-6-6"></a><span class="w"> </span>-H<span class="w"> </span><span class="s2">"Content-Type: application/json"</span><span class="w"> </span><span class="se">\</span>
|
||||
<a id="__codelineno-6-7" name="__codelineno-6-7" href="#__codelineno-6-7"></a><span class="w"> </span>-d<span class="w"> </span><span class="s1">'{</span>
|
||||
<a id="__codelineno-6-8" name="__codelineno-6-8" href="#__codelineno-6-8"></a><span class="s1"> "backend_type": "llama_cpp",</span>
|
||||
<a id="__codelineno-6-9" name="__codelineno-6-9" href="#__codelineno-6-9"></a><span class="s1"> "backend_options": {</span>
|
||||
<a id="__codelineno-6-10" name="__codelineno-6-10" href="#__codelineno-6-10"></a><span class="s1"> "model": "/path/to/model.gguf"</span>
|
||||
<a id="__codelineno-6-11" name="__codelineno-6-11" href="#__codelineno-6-11"></a><span class="s1"> }</span>
|
||||
<a id="__codelineno-6-12" name="__codelineno-6-12" href="#__codelineno-6-12"></a><span class="s1"> }'</span>
|
||||
<a id="__codelineno-6-13" name="__codelineno-6-13" href="#__codelineno-6-13"></a>
|
||||
<a id="__codelineno-6-14" name="__codelineno-6-14" href="#__codelineno-6-14"></a><span class="c1"># Start an instance</span>
|
||||
<a id="__codelineno-6-15" name="__codelineno-6-15" href="#__codelineno-6-15"></a>curl<span class="w"> </span>-X<span class="w"> </span>POST<span class="w"> </span>http://localhost:8080/api/instances/my-model/start
|
||||
</code></pre></div>
|
||||
<h2 id="openai-compatible-api">OpenAI Compatible API<a class="headerlink" href="#openai-compatible-api" title="Permanent link">¶</a></h2>
|
||||
<p>Llamactl provides OpenAI-compatible endpoints, making it easy to integrate with existing OpenAI client libraries and tools.</p>
|
||||
<h3 id="chat-completions">Chat Completions<a class="headerlink" href="#chat-completions" title="Permanent link">¶</a></h3>
|
||||
<p>Once you have an instance running, you can use it with the OpenAI-compatible chat completions endpoint:</p>
|
||||
<div class="highlight"><pre><span></span><code><a id="__codelineno-6-1" name="__codelineno-6-1" href="#__codelineno-6-1"></a>curl<span class="w"> </span>-X<span class="w"> </span>POST<span class="w"> </span>http://localhost:8080/v1/chat/completions<span class="w"> </span><span class="se">\</span>
|
||||
<a id="__codelineno-6-2" name="__codelineno-6-2" href="#__codelineno-6-2"></a><span class="w"> </span>-H<span class="w"> </span><span class="s2">"Content-Type: application/json"</span><span class="w"> </span><span class="se">\</span>
|
||||
<a id="__codelineno-6-3" name="__codelineno-6-3" href="#__codelineno-6-3"></a><span class="w"> </span>-d<span class="w"> </span><span class="s1">'{</span>
|
||||
<a id="__codelineno-6-4" name="__codelineno-6-4" href="#__codelineno-6-4"></a><span class="s1"> "model": "my-model",</span>
|
||||
<a id="__codelineno-6-5" name="__codelineno-6-5" href="#__codelineno-6-5"></a><span class="s1"> "messages": [</span>
|
||||
<a id="__codelineno-6-6" name="__codelineno-6-6" href="#__codelineno-6-6"></a><span class="s1"> {</span>
|
||||
<a id="__codelineno-6-7" name="__codelineno-6-7" href="#__codelineno-6-7"></a><span class="s1"> "role": "user",</span>
|
||||
<a id="__codelineno-6-8" name="__codelineno-6-8" href="#__codelineno-6-8"></a><span class="s1"> "content": "Hello! Can you help me write a Python function?"</span>
|
||||
<a id="__codelineno-6-9" name="__codelineno-6-9" href="#__codelineno-6-9"></a><span class="s1"> }</span>
|
||||
<a id="__codelineno-6-10" name="__codelineno-6-10" href="#__codelineno-6-10"></a><span class="s1"> ],</span>
|
||||
<a id="__codelineno-6-11" name="__codelineno-6-11" href="#__codelineno-6-11"></a><span class="s1"> "max_tokens": 150,</span>
|
||||
<a id="__codelineno-6-12" name="__codelineno-6-12" href="#__codelineno-6-12"></a><span class="s1"> "temperature": 0.7</span>
|
||||
<a id="__codelineno-6-13" name="__codelineno-6-13" href="#__codelineno-6-13"></a><span class="s1"> }'</span>
|
||||
<div class="highlight"><pre><span></span><code><a id="__codelineno-7-1" name="__codelineno-7-1" href="#__codelineno-7-1"></a>curl<span class="w"> </span>-X<span class="w"> </span>POST<span class="w"> </span>http://localhost:8080/v1/chat/completions<span class="w"> </span><span class="se">\</span>
|
||||
<a id="__codelineno-7-2" name="__codelineno-7-2" href="#__codelineno-7-2"></a><span class="w"> </span>-H<span class="w"> </span><span class="s2">"Content-Type: application/json"</span><span class="w"> </span><span class="se">\</span>
|
||||
<a id="__codelineno-7-3" name="__codelineno-7-3" href="#__codelineno-7-3"></a><span class="w"> </span>-d<span class="w"> </span><span class="s1">'{</span>
|
||||
<a id="__codelineno-7-4" name="__codelineno-7-4" href="#__codelineno-7-4"></a><span class="s1"> "model": "my-model",</span>
|
||||
<a id="__codelineno-7-5" name="__codelineno-7-5" href="#__codelineno-7-5"></a><span class="s1"> "messages": [</span>
|
||||
<a id="__codelineno-7-6" name="__codelineno-7-6" href="#__codelineno-7-6"></a><span class="s1"> {</span>
|
||||
<a id="__codelineno-7-7" name="__codelineno-7-7" href="#__codelineno-7-7"></a><span class="s1"> "role": "user",</span>
|
||||
<a id="__codelineno-7-8" name="__codelineno-7-8" href="#__codelineno-7-8"></a><span class="s1"> "content": "Hello! Can you help me write a Python function?"</span>
|
||||
<a id="__codelineno-7-9" name="__codelineno-7-9" href="#__codelineno-7-9"></a><span class="s1"> }</span>
|
||||
<a id="__codelineno-7-10" name="__codelineno-7-10" href="#__codelineno-7-10"></a><span class="s1"> ],</span>
|
||||
<a id="__codelineno-7-11" name="__codelineno-7-11" href="#__codelineno-7-11"></a><span class="s1"> "max_tokens": 150,</span>
|
||||
<a id="__codelineno-7-12" name="__codelineno-7-12" href="#__codelineno-7-12"></a><span class="s1"> "temperature": 0.7</span>
|
||||
<a id="__codelineno-7-13" name="__codelineno-7-13" href="#__codelineno-7-13"></a><span class="s1"> }'</span>
|
||||
</code></pre></div>
|
||||
<h3 id="using-with-python-openai-client">Using with Python OpenAI Client<a class="headerlink" href="#using-with-python-openai-client" title="Permanent link">¶</a></h3>
|
||||
<p>You can also use the official OpenAI Python client:</p>
|
||||
<div class="highlight"><pre><span></span><code><a id="__codelineno-7-1" name="__codelineno-7-1" href="#__codelineno-7-1"></a><span class="kn">from</span><span class="w"> </span><span class="nn">openai</span><span class="w"> </span><span class="kn">import</span> <span class="n">OpenAI</span>
|
||||
<a id="__codelineno-7-2" name="__codelineno-7-2" href="#__codelineno-7-2"></a>
|
||||
<a id="__codelineno-7-3" name="__codelineno-7-3" href="#__codelineno-7-3"></a><span class="c1"># Point the client to your Llamactl server</span>
|
||||
<a id="__codelineno-7-4" name="__codelineno-7-4" href="#__codelineno-7-4"></a><span class="n">client</span> <span class="o">=</span> <span class="n">OpenAI</span><span class="p">(</span>
|
||||
<a id="__codelineno-7-5" name="__codelineno-7-5" href="#__codelineno-7-5"></a> <span class="n">base_url</span><span class="o">=</span><span class="s2">"http://localhost:8080/v1"</span><span class="p">,</span>
|
||||
<a id="__codelineno-7-6" name="__codelineno-7-6" href="#__codelineno-7-6"></a> <span class="n">api_key</span><span class="o">=</span><span class="s2">"not-needed"</span> <span class="c1"># Llamactl doesn't require API keys by default</span>
|
||||
<a id="__codelineno-7-7" name="__codelineno-7-7" href="#__codelineno-7-7"></a><span class="p">)</span>
|
||||
<a id="__codelineno-7-8" name="__codelineno-7-8" href="#__codelineno-7-8"></a>
|
||||
<a id="__codelineno-7-9" name="__codelineno-7-9" href="#__codelineno-7-9"></a><span class="c1"># Create a chat completion</span>
|
||||
<a id="__codelineno-7-10" name="__codelineno-7-10" href="#__codelineno-7-10"></a><span class="n">response</span> <span class="o">=</span> <span class="n">client</span><span class="o">.</span><span class="n">chat</span><span class="o">.</span><span class="n">completions</span><span class="o">.</span><span class="n">create</span><span class="p">(</span>
|
||||
<a id="__codelineno-7-11" name="__codelineno-7-11" href="#__codelineno-7-11"></a> <span class="n">model</span><span class="o">=</span><span class="s2">"my-model"</span><span class="p">,</span> <span class="c1"># Use the name of your instance</span>
|
||||
<a id="__codelineno-7-12" name="__codelineno-7-12" href="#__codelineno-7-12"></a> <span class="n">messages</span><span class="o">=</span><span class="p">[</span>
|
||||
<a id="__codelineno-7-13" name="__codelineno-7-13" href="#__codelineno-7-13"></a> <span class="p">{</span><span class="s2">"role"</span><span class="p">:</span> <span class="s2">"user"</span><span class="p">,</span> <span class="s2">"content"</span><span class="p">:</span> <span class="s2">"Explain quantum computing in simple terms"</span><span class="p">}</span>
|
||||
<a id="__codelineno-7-14" name="__codelineno-7-14" href="#__codelineno-7-14"></a> <span class="p">],</span>
|
||||
<a id="__codelineno-7-15" name="__codelineno-7-15" href="#__codelineno-7-15"></a> <span class="n">max_tokens</span><span class="o">=</span><span class="mi">200</span><span class="p">,</span>
|
||||
<a id="__codelineno-7-16" name="__codelineno-7-16" href="#__codelineno-7-16"></a> <span class="n">temperature</span><span class="o">=</span><span class="mf">0.7</span>
|
||||
<a id="__codelineno-7-17" name="__codelineno-7-17" href="#__codelineno-7-17"></a><span class="p">)</span>
|
||||
<a id="__codelineno-7-18" name="__codelineno-7-18" href="#__codelineno-7-18"></a>
|
||||
<a id="__codelineno-7-19" name="__codelineno-7-19" href="#__codelineno-7-19"></a><span class="nb">print</span><span class="p">(</span><span class="n">response</span><span class="o">.</span><span class="n">choices</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span><span class="o">.</span><span class="n">message</span><span class="o">.</span><span class="n">content</span><span class="p">)</span>
|
||||
<div class="highlight"><pre><span></span><code><a id="__codelineno-8-1" name="__codelineno-8-1" href="#__codelineno-8-1"></a><span class="kn">from</span><span class="w"> </span><span class="nn">openai</span><span class="w"> </span><span class="kn">import</span> <span class="n">OpenAI</span>
|
||||
<a id="__codelineno-8-2" name="__codelineno-8-2" href="#__codelineno-8-2"></a>
|
||||
<a id="__codelineno-8-3" name="__codelineno-8-3" href="#__codelineno-8-3"></a><span class="c1"># Point the client to your Llamactl server</span>
|
||||
<a id="__codelineno-8-4" name="__codelineno-8-4" href="#__codelineno-8-4"></a><span class="n">client</span> <span class="o">=</span> <span class="n">OpenAI</span><span class="p">(</span>
|
||||
<a id="__codelineno-8-5" name="__codelineno-8-5" href="#__codelineno-8-5"></a> <span class="n">base_url</span><span class="o">=</span><span class="s2">"http://localhost:8080/v1"</span><span class="p">,</span>
|
||||
<a id="__codelineno-8-6" name="__codelineno-8-6" href="#__codelineno-8-6"></a> <span class="n">api_key</span><span class="o">=</span><span class="s2">"not-needed"</span> <span class="c1"># Llamactl doesn't require API keys by default</span>
|
||||
<a id="__codelineno-8-7" name="__codelineno-8-7" href="#__codelineno-8-7"></a><span class="p">)</span>
|
||||
<a id="__codelineno-8-8" name="__codelineno-8-8" href="#__codelineno-8-8"></a>
|
||||
<a id="__codelineno-8-9" name="__codelineno-8-9" href="#__codelineno-8-9"></a><span class="c1"># Create a chat completion</span>
|
||||
<a id="__codelineno-8-10" name="__codelineno-8-10" href="#__codelineno-8-10"></a><span class="n">response</span> <span class="o">=</span> <span class="n">client</span><span class="o">.</span><span class="n">chat</span><span class="o">.</span><span class="n">completions</span><span class="o">.</span><span class="n">create</span><span class="p">(</span>
|
||||
<a id="__codelineno-8-11" name="__codelineno-8-11" href="#__codelineno-8-11"></a> <span class="n">model</span><span class="o">=</span><span class="s2">"my-model"</span><span class="p">,</span> <span class="c1"># Use the name of your instance</span>
|
||||
<a id="__codelineno-8-12" name="__codelineno-8-12" href="#__codelineno-8-12"></a> <span class="n">messages</span><span class="o">=</span><span class="p">[</span>
|
||||
<a id="__codelineno-8-13" name="__codelineno-8-13" href="#__codelineno-8-13"></a> <span class="p">{</span><span class="s2">"role"</span><span class="p">:</span> <span class="s2">"user"</span><span class="p">,</span> <span class="s2">"content"</span><span class="p">:</span> <span class="s2">"Explain quantum computing in simple terms"</span><span class="p">}</span>
|
||||
<a id="__codelineno-8-14" name="__codelineno-8-14" href="#__codelineno-8-14"></a> <span class="p">],</span>
|
||||
<a id="__codelineno-8-15" name="__codelineno-8-15" href="#__codelineno-8-15"></a> <span class="n">max_tokens</span><span class="o">=</span><span class="mi">200</span><span class="p">,</span>
|
||||
<a id="__codelineno-8-16" name="__codelineno-8-16" href="#__codelineno-8-16"></a> <span class="n">temperature</span><span class="o">=</span><span class="mf">0.7</span>
|
||||
<a id="__codelineno-8-17" name="__codelineno-8-17" href="#__codelineno-8-17"></a><span class="p">)</span>
|
||||
<a id="__codelineno-8-18" name="__codelineno-8-18" href="#__codelineno-8-18"></a>
|
||||
<a id="__codelineno-8-19" name="__codelineno-8-19" href="#__codelineno-8-19"></a><span class="nb">print</span><span class="p">(</span><span class="n">response</span><span class="o">.</span><span class="n">choices</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span><span class="o">.</span><span class="n">message</span><span class="o">.</span><span class="n">content</span><span class="p">)</span>
|
||||
</code></pre></div>
|
||||
<h3 id="list-available-models">List Available Models<a class="headerlink" href="#list-available-models" title="Permanent link">¶</a></h3>
|
||||
<p>Get a list of running instances (models) in OpenAI-compatible format:</p>
|
||||
<div class="highlight"><pre><span></span><code><a id="__codelineno-8-1" name="__codelineno-8-1" href="#__codelineno-8-1"></a>curl<span class="w"> </span>http://localhost:8080/v1/models
|
||||
<div class="highlight"><pre><span></span><code><a id="__codelineno-9-1" name="__codelineno-9-1" href="#__codelineno-9-1"></a>curl<span class="w"> </span>http://localhost:8080/v1/models
|
||||
</code></pre></div>
|
||||
<h2 id="next-steps">Next Steps<a class="headerlink" href="#next-steps" title="Permanent link">¶</a></h2>
|
||||
<ul>
|
||||
@@ -1020,7 +1049,7 @@
|
||||
<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 21, 2025</span>
|
||||
<span class="git-revision-date-localized-plugin git-revision-date-localized-plugin-date">September 24, 2025</span>
|
||||
</span>
|
||||
|
||||
|
||||
|
||||
Reference in New Issue
Block a user