<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Rocm on skulldc</title><link>https://skulldc.net/tags/rocm/</link><description>Recent content in Rocm on skulldc</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Tue, 03 Nov 2026 00:14:14 +0000</lastBuildDate><atom:link href="https://skulldc.net/tags/rocm/index.xml" rel="self" type="application/rss+xml"/><item><title>vLLM v0.33.0rc3 drops CUDA 12.9, adds PyTorch 2.14, new models and speculative decoding gains</title><link>https://skulldc.net/2026/11/vllm-v0-33-0rc3-drops-cuda-12-9-adds-pytorch-2-14-new-models-and-specu/</link><pubDate>Tue, 03 Nov 2026 00:14:14 +0000</pubDate><guid>https://skulldc.net/2026/11/vllm-v0-33-0rc3-drops-cuda-12-9-adds-pytorch-2-14-new-models-and-specu/</guid><description>vLLM v0.33.0rc3 upgrades to PyTorch 2.14, moves to CUDA 13.0-only artifacts, adds 11 new models, and delivers speculative decoding and decode-speed improvements across NVIDIA and AMD hardware.</description></item></channel></rss>