Files
GenAIExamples/AgentQnA/kubernetes/helm/cpu-values.yaml
2025-04-15 14:27:12 +08:00

23 lines
683 B
YAML

# Copyright (C) 2025 Intel Corporation
# SPDX-License-Identifier: Apache-2.0
tgi:
enabled: false
vllm:
enabled: true
LLM_MODEL_ID: "meta-llama/Meta-Llama-3-8B-Instruct"
extraCmdArgs: ["--max-seq-len-to-capture", "16384", "--enable-auto-tool-choice", "--tool-call-parser", "llama3_json"]
supervisor:
llm_endpoint_url: http://{{ .Release.Name }}-vllm
llm_engine: vllm
model: "meta-llama/Meta-Llama-3-8B-Instruct"
ragagent:
llm_endpoint_url: http://{{ .Release.Name }}-vllm
llm_engine: vllm
model: "meta-llama/Meta-Llama-3-8B-Instruct"
sqlagent:
llm_endpoint_url: http://{{ .Release.Name }}-vllm
llm_engine: vllm
model: "meta-llama/Meta-Llama-3-8B-Instruct"