[Frontend] Port Step-3.5 parsers to the streaming parser engine (#59321)

Signed-off-by: sfeng33 <4florafeng@gmail.com>
This commit is contained in:
Flora Feng
2026-10-01 22:18:37 +00:00
committed by GitHub
parent ca65eb67d9
commit a5105dba05
12 changed files with 236 additions and 1647 deletions
+1
View File
@@ -29,6 +29,7 @@ vLLM currently supports the following reasoning models:
| [MiniMax-M2](https://huggingface.co/MiniMaxAI/MiniMax-M2) | `minimax_m2_append_think` | `json`, `regex` | ✅ |
| [Qwen3 series](https://huggingface.co/collections/Qwen/qwen3-67dd247413f0e2e4f653967f) | `qwen3` | `json`, `regex` | ✅ |
| [QwQ-32B](https://huggingface.co/Qwen/QwQ-32B) | `deepseek_r1` | `json`, `regex` | ✅ |
| [Step-3.5 / Step-3.7 Flash](https://huggingface.co/stepfun-ai/Step-3.5-Flash) | `step3p5` | `json`, `regex` | ✅ |
!!! note
IBM Granite 3.2 and DeepSeek-V3.1 reasoning is disabled by default; to enable it, you must also pass `thinking=True` in your `chat_template_kwargs`.
+12
View File
@@ -469,6 +469,18 @@ Use the checkpoint's chat template with `--tool-call-parser mimo --reasoning-par
For schema-constrained tool arguments, set `strict: true` inside each tool's `function`, or use `--tool-strict-level parameter`.
The parser supports `auto`, `required`, named tools, and `parallel_tool_calls=False`, preserving leading/trailing whitespace in string arguments.
### Step-3.5 and Step-3.7 Models (`step3p5`)
Supported models:
* `stepfun-ai/Step-3.5-Flash`
* `stepfun-ai/Step-3.5-Flash-FP8`
* `stepfun-ai/Step-3.7-Flash`
Flags: `--tool-call-parser step3p5 --reasoning-parser step3p5 --enable-auto-tool-choice`
The parser supports `auto`, `required`, and named tools.
### Olmo 3 Models (`olmo3`)
Olmo 3 models output tool calls in a format that is very similar to the one expected by the `pythonic` parser (see below), with a few differences. Each tool call is a pythonic string, but the parallel tool calls are newline-delimited, and the calls are wrapped within XML tags as `<function_calls>..</function_calls>`. In addition, the parser also allows JSON boolean and null literals (`true`, `false`, and `null`) in addition to the pythonic ones (`True`, `False`, and `None`).