chenchenghao/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 14 Packages Projects Releases Wiki Activity

[GLM-4.7] GLM-4.7 Tool Parser and Doc Update (#15333)

Browse Source
This commit is contained in:
Yuxuan Zhang
2025-12-19 20:30:44 -08:00
committed by GitHub
parent c0f9b51992
commit b82c7a0ae7
7 changed files with 849 additions and 434 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/advanced_features/server_arguments.md
+1 -1
View File
@@ -196,7 +196,7 @@ Please consult the documentation below and [server_args.py](https://github.com/s
| `--file-storage-path` | The path of the file storage in backend. | `sglang_storage` | Type: str |
| `--enable-cache-report` | Return number of cached tokens in usage.prompt_tokens_details for each openai request. | `False` | bool flag (set to enable) |
| `--reasoning-parser` | Specify the parser for reasoning models. Supported parsers: [deepseek-r1, deepseek-v3, glm45, gpt-oss, kimi, qwen3, qwen3-thinking, step3]. | `None` | `deepseek-r1`, `deepseek-v3`, `glm45`, `gpt-oss`, `kimi`, `qwen3`, `qwen3-thinking`, `step3` |
| `--tool-call-parser` | Specify the parser for handling tool-call interactions. Supported parsers: [deepseekv3, deepseekv31, glm, glm45, gpt-oss, kimi_k2, llama3, mistral, pythonic, qwen, qwen25, qwen3_coder, step3]. | `None` | `deepseekv3`, `deepseekv31`, `glm`, `glm45`, `gpt-oss`, `kimi_k2`, `llama3`, `mistral`, `pythonic`, `qwen`, `qwen25`, `qwen3_coder`, `step3` |
| `--tool-call-parser` | Specify the parser for handling tool-call interactions. Supported parsers: [deepseekv3, deepseekv31, glm, glm45, glm47, gpt-oss, kimi_k2, llama3, mistral, pythonic, qwen, qwen25, qwen3_coder, step3]. | `None` | `deepseekv3`, `deepseekv31`, `glm`, `glm45`, `glm47`, `gpt-oss`, `kimi_k2`, `llama3`, `mistral`, `pythonic`, `qwen`, `qwen25`, `qwen3_coder`, `step3` |
| `--sampling-defaults` | Where to get default sampling parameters. 'openai' uses SGLang/OpenAI defaults (temperature=1.0, top_p=1.0, etc.). 'model' uses the model's generation_config.json to get the recommended sampling parameters if available. Default is 'model'. | `model` | `openai`, `model` |
| `--tool-server` | Either 'demo' or a comma-separated list of tool server urls to use for the model. If not specified, no tool server will be used. | `None` | Type: str |
docs/basic_usage/glm45.md
+4 -2
View File
@@ -1,4 +1,4 @@
## Launch GLM-4.5 / GLM-4.6 with SGLang
## Launch GLM-4.5 / GLM-4.6 / GLM-4.7 with SGLang
To serve GLM-4.5 / GLM-4.6 FP8 models on 8xH100/H200 GPUs:
@@ -35,7 +35,9 @@ python3 -m sglang.launch_server \
--enable-custom-logit-processor
```
### Thinking Budget for GLM-4.5 / GLM-4.6
**Note**: For GLM-4.7, `--tool-call-parser` should be set to `glm47`, for GLM-4.5 and GLM-4.6, it should be set to `glm45`.
### Thinking Budget
In SGLang, we can implement thinking budget with `CustomLogitProcessor`.