# GPU Mode - 2026 强化学习迷你会议

Unsloth 的 GitHub，用于高效的 GRPO / GSPO，并包含大量自定义内核工作： <https://github.com/unslothai/unsloth>

以下是我们附上的 PDF 幻灯片：

{% file src="/files/74c53576aba9764d8f46a0052cfedad306700b3a" %}

### 强化学习资源

有关逐步指南、初学者或高级教程，您可以参考我们的文档：

{% columns %}
{% column width="50%" %}
{% content-ref url="/pages/7e8be22a966d3861ff1f7ebbd178ae7144d05c51" %}
[Reinforcement Learning Guide](/docs/zh/kai-shi-shi-yong/reinforcement-learning-rl-guide.md)
{% endcontent-ref %}

{% content-ref url="/pages/5aa66df0eeb87307aba670f22bb02189b4d9e37f" %}
[RL 奖励黑客](/docs/zh/kai-shi-shi-yong/reinforcement-learning-rl-guide/advanced-rl-documentation/rl-reward-hacking.md)
{% endcontent-ref %}
{% endcolumn %}

{% column width="50%" %}
{% content-ref url="/pages/6223874117c54cbdacd6f3467136ab1146fce98a" %}
[Advanced RL Docs](/docs/zh/kai-shi-shi-yong/reinforcement-learning-rl-guide/advanced-rl-documentation.md)
{% endcontent-ref %}

{% content-ref url="/pages/5487fa62e1aa76e8bf480388ee8d3305a4f0c4e1" %}
[RL 中的 FP16 与 BF16](/docs/zh/kai-shi-shi-yong/reinforcement-learning-rl-guide/advanced-rl-documentation/fp16-vs-bf16-for-rl.md)
{% endcontent-ref %}
{% endcolumn %}
{% endcolumns %}

{% columns %}
{% column width="50%" %}
{% content-ref url="/pages/f63218900ca62905f408a7e5cca35eb4279231d7" %}
[FP8 RL](/docs/zh/kai-shi-shi-yong/reinforcement-learning-rl-guide/fp8-reinforcement-learning.md)
{% endcontent-ref %}
{% endcolumn %}

{% column width="50%" %}
{% content-ref url="/pages/1d7550c0346dc79003c120cca2e0063a9addf768" %}
[Vision RL](/docs/zh/kai-shi-shi-yong/reinforcement-learning-rl-guide/vision-reinforcement-learning-vlm-rl.md)
{% endcontent-ref %}
{% endcolumn %}
{% endcolumns %}

### 直播视频录制

{% embed url="<https://www.youtube.com/watch?v=jMSCJZAEYR8>" %}


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://unsloth.ai/docs/zh/bo-ke/gpu-mode-conference.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.