Patch release: v5.5.3

<p>Small patch dedicated to optimizing gemma4, fixing inference with <code>use_cache=False</code> due to k/v states sharing between layers, as well as conversion mappings for some

<h2>What's Changed</h2> <p>Another fix for qwen vl models that prevented correctly loading the associated model type - this works together with <a class="issue-link js-issue-link"

<h1>Patch release v5.14.1</h1> <p>This patch solves a few issues which appeared when integrating Inkling model, most notably an issue affecting models using EncoderDecoderCache

<h1>Patch release v5.6.2</h1> <p>Qwen 3.5 and 3.6 MoE (text-only) were broken when using with FP8. It should now work again with this 🫡</p> <ul> <li>Fix configuration reading and

<h1>Patch release v5.12.1</h1> <p>Updated the lower bound for PEFT and a fix for auto tokenizer to properly resolve the mistral tokenizer (when <code>mistral-common</code> is

<h1>Patch release v5.8.1</h1> <p>This release is mainly to fix the Deepseek V4 integration!!!</p> <a

<h1>Patch release v5.6.1</h1> <p>Flash attention path was broken! Sorry everyone for this one 🤗</p> <ul> <li>Fix AttributeError on s_aux=None in flash_attention_forward (<a