# 推测解码

## :llama:llama.cpp、llama-server 中的投机性解码

可以通过以下方式在 llama.cpp 中轻松启用投机性解码 `llama-cli` 和 `llama-server` 通过 `--model-draft` 参数。注意您必须有一个草稿模型，通常是一个较小的模型，但它必须使用相同的分词器 

### GLM 4.7 的投机性解码

```python
# !pip install huggingface_hub hf_transfer
import os
os.environ["HF_HUB_ENABLE_HF_TRANSFER"] = "0" # 有时会限流，因此设置为 0 以禁用
from huggingface_hub import snapshot_download
snapshot_download(
    repo_id = "unsloth/GLM-4.7-GGUF",
    local_dir = "unsloth/GLM-4.7-GGUF",
    allow_patterns = ["*UD-Q2_K_XL*"], # 动态 2 位。对于动态 1 位使用 "*UD-TQ1_0*"
)
snapshot_download(
    repo_id = "unsloth/GLM-4.5-Air-GGUF",
    local_dir = "unsloth/GLM-4.5-Air-GGUF",
    allow_patterns = ["*UD-Q4_K_XL*"], # 动态 4 位。对于动态 1 位使用 "*UD-TQ1_0*"
)
```

{% code overflow="wrap" %}

```bash
./llama.cpp/llama-cli \
    --model unsloth/GLM-4.7-GGUF/UD-Q2_K_XL/GLM-4.7-UD-Q2_K_XL-00001-of-00003.gguf \
    --threads -1 \
    --fit on \
    --prio 3 \
    --temp 1.0 \
    --top-p 0.95 \
    --ctx-size 16384 \
    --jinja
```

{% endcode %}

<figure><img src="/files/80b10baa78a774e83c0372cf3e545043a1bb0368" alt=""><figcaption></figcaption></figure>

{% code overflow="wrap" %}

```bash
./llama.cpp/llama-cli \
    --model unsloth/GLM-4.7-GGUF/UD-Q2_K_XL/GLM-4.7-UD-Q2_K_XL-00001-of-00003.gguf \
    --model-draft unsloth/GLM-4.5-Air-GGUF/UD-Q4_K_XL/GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002.gguf \
    --threads -1 \
    --fit on \
    --prio 3 \
    --temp 1.0 \
    --top-p 0.95 \
    --ctx-size 16384 \
    --ctx-size-draft 16384 \
    --jinja \
    --device CUDA0 \
    --device-draft CUDA0,CUDA1
```

{% endcode %}

{% code overflow="wrap" %}

```bash
./llama.cpp/llama-server \
    --model unsloth/GLM-4.7-GGUF/UD-Q2_K_XL/GLM-4.7-UD-Q2_K_XL-00001-of-00003.gguf \
    --alias "unsloth/GLM-4.7" \
    --threads -1 \
    --fit on \
    --prio 3 \
    --temp 1.0 \
    --top-p 0.95 \
    --ctx-size 16384 \
    --port 8001 \
    --jinja
```

{% endcode %}


---

# 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/ji-chu/inference-and-deployment/saving-to-gguf/speculative-decoding.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.