> For the complete documentation index, see [llms.txt](https://unsloth.ai/docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://unsloth.ai/docs/zh/bo-ke.md).

# 博客

- [使用 Unsloth Kernels + Packing 实现 3 倍更快的 LLM 训练](https://unsloth.ai/docs/zh/bo-ke/3x-faster-training-packing.md): 了解 Unsloth 如何提升训练吞吐量，并消除微调中的填充浪费。
- [50 万上下文长度微调](https://unsloth.ai/docs/zh/bo-ke/500k-context-length-fine-tuning.md): 了解如何使用 Unsloth 启用超过 50 万 token 的上下文窗口微调。
- [量化感知训练（QAT）](https://unsloth.ai/docs/zh/bo-ke/quantization-aware-training-qat.md): 使用 Unsloth 和 PyTorch 将模型量化为 4 位，以恢复准确率。
- [在 NVIDIA DGX Station 上使用 Unsloth 微调 LLM](https://unsloth.ai/docs/zh/bo-ke/dgx-station.md): NVIDIA DGX Station 教程：如何使用 Unsloth 的 notebooks 进行微调。
- [如何使用 Unsloth 和 Docker 微调 LLM](https://unsloth.ai/docs/zh/bo-ke/how-to-fine-tune-llms-with-unsloth-and-docker.md): 了解如何使用 Unsloth 的 Docker 镜像微调 LLM 或进行强化学习（RL）。
- [使用 NVIDIA DGX Spark 和 Unsloth 微调 LLM](https://unsloth.ai/docs/zh/bo-ke/fine-tuning-llms-with-nvidia-dgx-spark-and-unsloth.md): 关于如何在 NVIDIA DGX Spark 上使用 OpenAI gpt-oss 进行微调和强化学习（RL）的教程。
- [使用 Blackwell、RTX 50 系列和 Unsloth 微调 LLM](https://unsloth.ai/docs/zh/bo-ke/fine-tuning-llms-with-blackwell-rtx-50-series-and-unsloth.md): 通过我们的分步指南，了解如何在 NVIDIA Blackwell RTX 50 系列和 B200 GPU 上微调 LLM。
- [如何在 ComfyUI 中运行 Diffusion Image GGUF](https://unsloth.ai/docs/zh/bo-ke/comfyui.md): 在 ComfyUI 中运行 Unsloth Diffusion GGUF 模型的指南。
- [AI Engineer's 2025](https://unsloth.ai/docs/zh/bo-ke/ai-engineers-2025.md): 我们在 AI Engineer's Worlds Fair 2025 工作坊的幻灯片。
- [Unsloth - AI Engineer World's Fair 2026](https://unsloth.ai/docs/zh/bo-ke/ai-engineer-2026.md): 我们在 AI Engineer's Worlds Fair 2026 工作坊的幻灯片。
- [GPU Mode - Reinforcement Learning Mini Conference 2026](https://unsloth.ai/docs/zh/bo-ke/gpu-mode-conference.md): 我们在 PyTorch Conference 2025 演讲的幻灯片。
- [Unsloth AMD PyTorch 合成数据黑客松](https://unsloth.ai/docs/zh/bo-ke/unsloth-amd-pytorch-synthetic-data-hackathon.md): 在 AMD GPU 上运行 Unsloth 的技巧、故障排查和指南。
- [PyTorch Conference 2025 - Unsloth](https://unsloth.ai/docs/zh/bo-ke/pytorch-conference-2025-unsloth.md): 我们在 PyTorch Conference 2025 演讲的幻灯片。


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## 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, and the optional `goal` query parameter:

```
GET https://unsloth.ai/docs/zh/bo-ke.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

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.