<?xml version="1.0" encoding="UTF-8"?>
<rss version="2.0">
  <channel>
    <title>PyPI recent updates for mojolearn</title>
    <link>https://pypi.org/project/mojolearn/</link>
    <description>Recent updates to the Python Package Index for mojolearn</description>
    <language>en</language>    <item>
      <title>0.6.0</title>
      <link>https://pypi.org/project/mojolearn/0.6.0/</link>
      <description>GPU machine learning in Mojo for Metal, CUDA, and HIP, with fast, deterministic, and cross-vendor identical modes for certified configurations</description>
      <pubDate>Sun, 06 Sep 2026 23:23:11 GMT</pubDate>
    </item>    <item>
      <title>0.5.0</title>
      <link>https://pypi.org/project/mojolearn/0.5.0/</link>
      <description>GPU machine learning in Mojo for Metal, CUDA, and HIP, with fast, deterministic, and cross-vendor identical modes for certified configurations</description>
      <pubDate>Sat, 05 Sep 2026 10:14:53 GMT</pubDate>
    </item>    <item>
      <title>0.3.1</title>
      <link>https://pypi.org/project/mojolearn/0.3.1/</link>
      <description>GPU machine learning in Mojo. Gradient boosting, random forests, extra trees, SVM, k-means, k-NN, DBSCAN, PCA, hierarchical and spectral clustering, GLMs, scoring metrics and an FP32 matmul, on Apple silicon through Metal and from the same source on NVIDIA and AMD. Three numeric modes per estimator: fast, deterministic (same bits every run) and identical (same bits on every GPU vendor)</description>
      <pubDate>Mon, 31 Aug 2026 16:38:42 GMT</pubDate>
    </item>    <item>
      <title>0.3.0</title>
      <link>https://pypi.org/project/mojolearn/0.3.0/</link>
      <description>GPU machine learning in Mojo. Gradient boosting, random forests, extra trees, SVM, k-means, k-NN, DBSCAN, PCA, hierarchical and spectral clustering, GLMs, scoring metrics and an FP32 matmul, on Apple silicon through Metal and from the same source on NVIDIA and AMD. Three numeric modes per estimator: fast, deterministic (same bits every run) and identical (same bits on every GPU vendor)</description>
      <pubDate>Sun, 30 Aug 2026 22:16:30 GMT</pubDate>
    </item>    <item>
      <title>0.2.0</title>
      <link>https://pypi.org/project/mojolearn/0.2.0/</link>
      <description>GPU machine learning in Mojo. Gradient boosting, random forests, extra trees, SVM, k-means, k-NN, DBSCAN, PCA, hierarchical and spectral clustering, GLMs, scoring metrics and an FP32 matmul, on Apple silicon through Metal and from the same source on NVIDIA and AMD. Three numeric modes per estimator: fast, deterministic (same bits every run) and identical (same bits on every GPU vendor)</description>
      <pubDate>Sun, 30 Aug 2026 07:48:58 GMT</pubDate>
    </item>    <item>
      <title>0.1.0</title>
      <link>https://pypi.org/project/mojolearn/0.1.0/</link>
      <description>GPU machine learning in Mojo. Gradient boosting, random forests, extra trees, k-means, k-NN, DBSCAN, PCA and OLS on Apple silicon, bit-identical across GPU vendors on request</description>
      <pubDate>Sun, 23 Aug 2026 12:34:20 GMT</pubDate>
    </item>  </channel>
</rss>