tag:github.com,2008:https://github.com/intentee/paddler/releasesRelease notes from paddler2026-01-03T13:52:06Ztag:github.com,2008:Repository/792847444/v2.1.12026-01-06T19:52:58ZOpenAI compatibility improvements<ul>
<li>Thank you <a class="user-mention notranslate" data-hovercard-type="user" data-hovercard-url="/users/jason-ni/hovercard" data-octo-click="hovercard-link-click" data-octo-dimensions="link_type:self" href="https://github.com/jason-ni">@jason-ni</a> for the contribution: <a class="issue-link js-issue-link" data-error-text="Failed to load title" data-id="3777941351" data-permission-text="Title is private" data-url="https://github.com/intentee/paddler/issues/152" data-hovercard-type="pull_request" data-hovercard-url="/intentee/paddler/pull/152/hovercard" href="https://github.com/intentee/paddler/pull/152">#152</a></li>
</ul>github-actions[bot]tag:github.com,2008:Repository/792847444/v2.1.1-rc12026-01-06T19:42:09ZOpenAI compatibility improvements<ul>
<li>Thank you <a class="user-mention notranslate" data-hovercard-type="user" data-hovercard-url="/users/jason-ni/hovercard" data-octo-click="hovercard-link-click" data-octo-dimensions="link_type:self" href="https://github.com/jason-ni">@jason-ni</a> for the contribution: <a class="issue-link js-issue-link" data-error-text="Failed to load title" data-id="3777941351" data-permission-text="Title is private" data-url="https://github.com/intentee/paddler/issues/152" data-hovercard-type="pull_request" data-hovercard-url="/intentee/paddler/pull/152/hovercard" href="https://github.com/intentee/paddler/pull/152">#152</a></li>
</ul>github-actions[bot]tag:github.com,2008:Repository/792847444/v2.1.02025-08-13T13:01:30Zv2.1.0<h2>License switch</h2>
<p>The license was switched from <strong>MIT</strong> to <strong>Apache-2.0</strong>, which is more permissive (has explicit patent grants), so it should be easier to adopt in organizations.</p>
<h2>Features</h2>
<ul>
<li><a href="https://paddler.intentee.com/docs/migrating-to-paddler/openai-compatibility/" rel="nofollow">OpenAI compatibility</a> endpoint:
<ul>
<li>Support for <code>max_completion_tokens</code> parameter in /v1/chat/completions endpoint</li>
<li>Support for <code>messages</code> parameter in /v1/chat/completions endpoint</li>
<li>Support for <code>stream</code> parameter in /v1/chat/completions endpoint</li>
</ul>
</li>
</ul>
<p>Documentation: <a href="https://paddler.intentee.com/docs/migrating-to-paddler/openai-compatibility/" rel="nofollow">https://paddler.intentee.com/docs/migrating-to-paddler/openai-compatibility/</a></p>
<p><strong>Full Changelog</strong>: <a class="commit-link" href="https://github.com/intentee/paddler/compare/v2.0.0...v2.1.0"><tt>v2.0.0...v2.1.0</tt></a></p>github-actions[bot]tag:github.com,2008:Repository/792847444/v2.0.02025-08-08T19:47:01Zv2.0.0<h2>What's Changed</h2>
<p>Long story short, we rewrote most of the <code>llama-server</code>, made it scalable, and bundled that with Paddler. This means you do not have to deploy <code>llama-server</code> alongside Paddler anymore (the fewer moving parts, the better). :)</p>
<p>We also have a new, vastly improved admin panel, and a lot of other fixes, improvements, and changes.</p>
<p><strong>Full Changelog</strong>: <a class="commit-link" href="https://github.com/intentee/paddler/compare/v1.2.1-rc1...v2.0.0"><tt>v1.2.1-rc1...v2.0.0</tt></a></p>github-actions[bot]tag:github.com,2008:Repository/792847444/v2.0.0-rc12025-08-08T19:42:22Zv2.0.0-rc1<h2>What's Changed</h2>
<p>Long story short, we rewrote most of the <code>llama-server</code>, made it scalable, and bundled that with Paddler. This means you do not have to deploy <code>llama-server</code> alongside Paddler anymore (the fewer moving parts, the better). :)</p>
<p>We also have a new, vastly improved admin panel, and a lot of other fixes, improvements, and changes.</p>
<p><strong>Full Changelog</strong>: <a class="commit-link" href="https://github.com/intentee/paddler/compare/v1.2.1-rc1...v2.0.0-rc1"><tt>v1.2.1-rc1...v2.0.0-rc1</tt></a></p>github-actions[bot]tag:github.com,2008:Repository/792847444/v1.2.1-rc12025-06-10T15:16:50Zv1.2.1-rc1<h1>Fixes</h1>
<ul>
<li>Fix overflow/underflow issues when managing slots</li>
</ul>github-actions[bot]tag:github.com,2008:Repository/792847444/v1.2.02024-12-07T13:20:57Zv1.2.0<h1>Features</h1>
<ul>
<li>Add TUI dashboard (<code>paddler dashboard --management-addr [HOST]:[PORT]</code>) to be able to easily observe balancer instances from the terminal level (thank you <a class="user-mention notranslate" data-hovercard-type="user" data-hovercard-url="/users/Propfend/hovercard" data-octo-click="hovercard-link-click" data-octo-dimensions="link_type:self" href="https://github.com/Propfend">@Propfend</a> for the <a href="https://github.com/distantmagic/paddler/pull/31" data-hovercard-type="pull_request" data-hovercard-url="/intentee/paddler/pull/31/hovercard">contribution</a>!)</li>
</ul>github-actions[bot]tag:github.com,2008:Repository/792847444/v1.1.02024-11-23T12:38:39Zv1.1.0<ul>
<li>More meaningful error messages when the agent can't connect to the llama.cpp slot endpoint, or when slot endpoint is not enabled in llama.cpp</li>
<li>Set default logging level to <code>info</code> for agents and balancer to increase the amount of information in the logs (it wasn't clean if the agent was running or not)</li>
<li>Enable LTO optimization for the release builds (see <a href="https://github.com/distantmagic/paddler/issues/28" data-hovercard-type="issue" data-hovercard-url="/intentee/paddler/issues/28/hovercard">#28</a>) (thank you <a class="user-mention notranslate" data-hovercard-type="user" data-hovercard-url="/users/zamazan4ik/hovercard" data-octo-click="hovercard-link-click" data-octo-dimensions="link_type:self" href="https://github.com/zamazan4ik">@zamazan4ik</a>)</li>
</ul>github-actions[bot]tag:github.com,2008:Repository/792847444/v1.0.02024-11-20T20:53:41Zv1.0.0<p>Paddler is now rewritten in Rust and uses the <a href="https://github.com/cloudflare/pingora">Pingora</a> framework for the networking stack. A few minor API changes and reporting improvements are introduced (documented in the README).</p>
<p>This is a stability/quality release that solves some memory related issues, and makes the balancer more resilient to agents randomly going up/down.</p>github-actions[bot]tag:github.com,2008:Repository/792847444/v1.0.0-rc12024-11-20T20:46:04Zv1.0.0-rc1No content.github-actions[bot]