A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 15, 09:45 UTC
[doc] update reasoning doc (#18306)
Signed-off-by: reidliu41 <reid201711@gmail.com> Co-authored-by: reidliu41 <reid201711@gmail.com>
Reid committed
May 18, 2025 at 21:59 UTC
1a8f68bb9035b5c399b6074a00e6e2f20dcdcced
1 file changed
+3
-4
docs/source/features/reasoning_outputs.md
+3
-4
@@ -231,13 +231,12 @@ For more examples, please refer to <gh-file:examples/online_serving/openai_chat_
231
232
## How to support a new reasoning model
233
234
-You can add a new `ReasoningParser` similar to <gh-file:vllm/entrypoints/openai/reasoning_parsers/deepseek_r1_reasoning_parser.py>.
234
+You can add a new `ReasoningParser` similar to <gh-file:vllm/reasoning/deepseek_r1_reasoning_parser.py>.
235
236
```python
237
# import the required packages
238
239
-from vllm.entrypoints.openai.reasoning_parsers.abs_reasoning_parsers import (
240
- ReasoningParser, ReasoningParserManager)
239
+from vllm.reasoning import ReasoningParser, ReasoningParserManager
240
from vllm.entrypoints.openai.protocol import (ChatCompletionRequest,
241
DeltaMessage)
242
@@ -288,7 +287,7 @@ class ExampleParser(ReasoningParser):
287
"""
288
```
289
291
-Additionally, to enable structured output, you'll need to create a new `Reasoner` similar to the one in <gh-file:vllm/model_executor/guided_decoding/reasoner/deepseek_reasoner.py>.
290
+Additionally, to enable structured output, you'll need to create a new `Reasoner` similar to the one in <gh-file:vllm/reasoning/deepseek_r1_reasoning_parser.py>.
291
292
```python
293
@dataclass