diff --git a/deploy/b300-k8s/dynamo/start_dynamo_pd.sh b/deploy/b300-k8s/dynamo/start_dynamo_pd.sh index 59f545fe7f..a9aa1f862e 100755 --- a/deploy/b300-k8s/dynamo/start_dynamo_pd.sh +++ b/deploy/b300-k8s/dynamo/start_dynamo_pd.sh @@ -118,6 +118,7 @@ docker run -d --name dyn-p --gpus all -e CUDA_VISIBLE_DEVICES=0,1,2,3 \ --trust-remote-code --tokenizer-backend fastokens \ --model-path "$MODEL" --served-model-name "$SERVED" \ --reasoning-parser auto --tool-call-parser auto \ + --dyn-default-thinking-mode enabled \ --default-chat-template-kwargs '{"thinking": true, "reasoning_effort": "high"}' \ --tp 4 --dp-size 4 --ep-size 4 --enable-dp-attention --enable-dp-lm-head \ --moe-a2a-backend megamoe --dsv4-attn-backend flashmla_mega \ @@ -157,6 +158,7 @@ docker run -d --name dyn-d --gpus all -e CUDA_VISIBLE_DEVICES=4,5,6,7 \ --trust-remote-code --tokenizer-backend fastokens \ --model-path "$MODEL" --served-model-name "$SERVED" \ --reasoning-parser auto --tool-call-parser auto \ + --dyn-default-thinking-mode enabled \ --tp 4 --dp-size 4 --ep-size 4 --enable-dp-attention --enable-dp-lm-head \ --enable-fp32-lm-head --enable-dp-attention-local-control-broadcast \ --moe-a2a-backend megamoe --dsv4-attn-backend flashmla_mega \