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 1, 21:15 UTC
[Reasoning][Structured Outputs] Add Command A plus tags for structural tags (#44588)
Signed-off-by: rishitdholakia13 <rishit+github@cohere.com> Co-authored-by: Chauncey <chaunceyjiang@gmail.com>
rishitdholakia13 committed
Jun 5, 2026 at 09:51 UTC
6a11d72df7f15b39d76570dba5f415ff2b0292b3
1 file changed
+1
-1
vllm/reasoning/cohere_command_reasoning_parser.py
+1
-1
@@ -90,7 +90,7 @@ MODEL_TO_TAG_STYLE: dict[str, CohereTagStyle] = {
90
tools=COMMAND_A_TOOLS_TAG,
91
),
92
"Cohere2MoeForCausalLM": CohereTagStyle(
93
- json_tags=(COMMAND_A_JSON_TAG,),
93
+ json_tags=(COMMAND_A_JSON_TAG, COMMAND_A_PLUS_JSON_TAG),
94
tools=COMMAND_A_TOOLS_TAG,
95
),
96
}