Update dev-corp inventory configuration
This commit is contained in:
toki
parent
ae4819046e
commit
469d2f32b4
1 changed files with 63 additions and 24 deletions
|
|
@ -117,7 +117,7 @@ model:
|
|||
adapter_mapping: vllm_and_vllm_mlx_use_chat_template_kwargs_enable_thinking_true
|
||||
direct_ornith_profile:
|
||||
observed_at: "2026-07-13"
|
||||
status: active_direct_only_not_iop_connected
|
||||
status: active_direct_only_via_mac_mini_port_forward_not_iop_connected
|
||||
family: spark_ornith
|
||||
model_id: ornith:35b
|
||||
display_name: Ornith 1.0 35B FP8 Direct vLLM
|
||||
|
|
@ -144,6 +144,8 @@ model:
|
|||
spark01:
|
||||
provider: dev-corp-spark01-ornith
|
||||
endpoint: http://192.168.2.2:8003/v1
|
||||
pi_forward_base_url_current_host: http://172.24.63.178:18003/v1
|
||||
pi_forward_base_url_runner: http://127.0.0.1:18003/v1
|
||||
health: http://192.168.2.2:8003/health
|
||||
container_name: iop-vllm-ornith35b-fp8
|
||||
start_script: /home/digitalcommerce_dgx_spark_01/start_vllm_ornith35b_docker_8003.sh
|
||||
|
|
@ -165,6 +167,8 @@ model:
|
|||
spark02:
|
||||
provider: dev-corp-spark02-ornith
|
||||
endpoint: http://192.168.2.4:8005/v1
|
||||
pi_forward_base_url_current_host: http://172.24.63.178:18005/v1
|
||||
pi_forward_base_url_runner: http://127.0.0.1:18005/v1
|
||||
health: http://192.168.2.4:8005/health
|
||||
container_name: iop-vllm-ornith35b-fp8
|
||||
start_script: /home/dplab/start_vllm_ornith35b_docker_8005.sh
|
||||
|
|
@ -190,6 +194,31 @@ model:
|
|||
default_provider: dev-corp-spark01-ornith
|
||||
default_model: ornith:35b
|
||||
default_thinking_level: high
|
||||
route_policy: current host Pi must use the mac-mini 172.24.63.178 port-forward endpoints, not the provider-internal 192.168.2.x addresses.
|
||||
port_forward:
|
||||
runner: fe@172.24.63.178
|
||||
script: /Users/fe/server/start_port_forward.sh
|
||||
restart_command: cd ~/server && ./start_port_forward.sh spark_01 && ./start_port_forward.sh spark_02
|
||||
sshpass_path_note: non-login SSH uses /opt/homebrew/bin/sshpass fallback in the script.
|
||||
forwards:
|
||||
spark01:
|
||||
provider: dev-corp-spark01-ornith
|
||||
current_host_base_url: http://172.24.63.178:18003/v1
|
||||
runner_local_base_url: http://127.0.0.1:18003/v1
|
||||
provider_internal_base_url: http://192.168.2.2:8003/v1
|
||||
spark02:
|
||||
provider: dev-corp-spark02-ornith
|
||||
current_host_base_url: http://172.24.63.178:18005/v1
|
||||
runner_local_base_url: http://127.0.0.1:18005/v1
|
||||
provider_internal_base_url: http://192.168.2.4:8005/v1
|
||||
validation:
|
||||
current_host_models:
|
||||
spark01: ornith:35b
|
||||
spark02: ornith:35b
|
||||
current_host_chat_completions_no_thinking:
|
||||
spark01: ORNITH_OK
|
||||
spark02: ORNITH_OK
|
||||
pi_direct_print: PI_ORNITH_172_OK
|
||||
enabled_model_patterns:
|
||||
- dev-corp-spark02-ornith/*
|
||||
- dev-corp-spark01-ornith/*
|
||||
|
|
@ -198,15 +227,17 @@ model:
|
|||
- dev-corp/*
|
||||
providers:
|
||||
dev-corp-spark01-ornith:
|
||||
base_url: http://192.168.2.2:8003/v1
|
||||
base_url: http://172.24.63.178:18003/v1
|
||||
provider_internal_base_url: http://192.168.2.2:8003/v1
|
||||
model_id: ornith:35b
|
||||
dev-corp-spark02-ornith:
|
||||
base_url: http://192.168.2.4:8005/v1
|
||||
base_url: http://172.24.63.178:18005/v1
|
||||
provider_internal_base_url: http://192.168.2.4:8005/v1
|
||||
model_id: ornith:35b
|
||||
api_key_value_tracked: false
|
||||
iop_connection_status: not_connected_pending_separate_step
|
||||
pi_agent_profile:
|
||||
observed_at: "2026-07-10"
|
||||
observed_at: "2026-07-13"
|
||||
config_scope: host_local_pi_agent
|
||||
config_dir: ~/.pi/agent
|
||||
install:
|
||||
|
|
@ -217,16 +248,22 @@ model:
|
|||
models_file: ~/.pi/agent/models.json
|
||||
extension_files:
|
||||
- ~/.pi/agent/extensions/dev-corp-temperature.ts
|
||||
profile_namespace: dev_corp_gemma4_pi
|
||||
current_default_provider: dev-corp
|
||||
current_default_model: gemma4:26b
|
||||
current_default_runtime: edge_openai_compatible_provider_pool
|
||||
current_default_base_url: http://digitalplatform.iop.ai.kr:18086/v1
|
||||
profile_namespace: dev_corp_spark_ornith_pi
|
||||
current_default_provider: dev-corp-spark01-ornith
|
||||
current_default_model: ornith:35b
|
||||
current_default_runtime: spark_ornith_direct_via_mac_mini_port_forward
|
||||
current_default_base_url: http://172.24.63.178:18003/v1
|
||||
current_default_api: openai-completions
|
||||
current_default_auth_header: true
|
||||
current_default_thinking_level: high
|
||||
current_default_temperature: 0.2
|
||||
current_default_top_p: 0.95
|
||||
current_default_temperature: null
|
||||
current_default_top_p: null
|
||||
current_default_sampling_parameter_source: none_for_direct_ornith
|
||||
edge_provider_pool_fallback:
|
||||
provider: dev-corp
|
||||
model_id: gemma4:26b
|
||||
base_url: http://digitalplatform.iop.ai.kr:18086/v1
|
||||
sampling_parameter_source: before_provider_request extension dev-corp-temperature.ts
|
||||
hide_thinking_block: false
|
||||
http_idle_timeout_ms: 300000
|
||||
retry_provider_timeout_ms: 300000
|
||||
|
|
@ -245,26 +282,26 @@ model:
|
|||
scope: dev-corp provider only
|
||||
effect: inject temperature 0.2 and top_p 0.95 into provider request payload
|
||||
api_key_value_tracked: false
|
||||
route_policy: current dev-corp Pi default must use the public Edge route iop.ai.kr.
|
||||
route_policy: current dev-corp Pi default uses mac-mini 172.24.63.178 port-forward endpoints for Spark Ornith direct; public Edge dev-corp/gemma4 remains a separate fallback provider profile.
|
||||
pi_model_parameters:
|
||||
provider: dev-corp
|
||||
model_id: gemma4:26b
|
||||
display_name: dev-corp gemma4:26b
|
||||
provider: dev-corp-spark01-ornith
|
||||
model_id: ornith:35b
|
||||
display_name: dev-corp Spark 01 Ornith 1.0 35B FP8
|
||||
api: openai-completions
|
||||
context_window: 262144
|
||||
max_tokens: 32768
|
||||
reasoning: true
|
||||
thinking_level: high
|
||||
request_temperature: 0.2
|
||||
request_top_p: 0.95
|
||||
sampling_parameter_source: before_provider_request extension dev-corp-temperature.ts
|
||||
expected_iop_thinking_token_budget: 1024
|
||||
request_temperature: null
|
||||
request_top_p: null
|
||||
sampling_parameter_source: none_for_direct_ornith
|
||||
expected_iop_thinking_token_budget: null
|
||||
compat:
|
||||
supports_developer_role: false
|
||||
supports_usage_in_streaming: false
|
||||
max_tokens_field: max_tokens
|
||||
supports_reasoning_effort: false
|
||||
supports_strict_mode: false
|
||||
supports_strict_mode: true
|
||||
supports_store: false
|
||||
requires_tool_result_name: true
|
||||
requires_assistant_after_tool_result: true
|
||||
|
|
@ -295,10 +332,11 @@ model:
|
|||
dgx_spark_01_ornith_direct:
|
||||
provider: dev-corp-spark01-ornith
|
||||
default_provider: true
|
||||
base_url: http://192.168.2.2:8003/v1
|
||||
base_url: http://172.24.63.178:18003/v1
|
||||
provider_internal_base_url: http://192.168.2.2:8003/v1
|
||||
served_model: ornith:35b
|
||||
runtime: dgx_spark_01_ornith_direct
|
||||
route_note: direct-only Pi provider before IOP connection; do not treat it as the Edge alias route
|
||||
route_note: direct-only Pi provider before IOP connection; current host reaches it through mac-mini port-forward, not the provider-internal 192.168.2.x address
|
||||
compat:
|
||||
supports_strict_mode: true
|
||||
supports_developer_role: false
|
||||
|
|
@ -311,10 +349,11 @@ model:
|
|||
dgx_spark_02_ornith_direct:
|
||||
provider: dev-corp-spark02-ornith
|
||||
default_provider: false
|
||||
base_url: http://192.168.2.4:8005/v1
|
||||
base_url: http://172.24.63.178:18005/v1
|
||||
provider_internal_base_url: http://192.168.2.4:8005/v1
|
||||
served_model: ornith:35b
|
||||
runtime: dgx_spark_02_ornith_direct
|
||||
route_note: direct-only Pi provider before IOP connection; Spark02 North was stopped for memory headroom while Gemma4 8004 remained healthy
|
||||
route_note: direct-only Pi provider before IOP connection; current host reaches it through mac-mini port-forward, and Spark02 North was stopped for memory headroom while Gemma4 8004 remained healthy
|
||||
compat:
|
||||
supports_strict_mode: true
|
||||
supports_developer_role: false
|
||||
|
|
|
|||
Loading…
Reference in a new issue