toki/iop
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Merge branch 'main' of https://git.toki-labs.com/toki/iop

Browse source
This commit is contained in:
toki 2026-07-13 06:25:59 +09:00
commit ae4819046e
1 changed files with 125 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

126
agent-test/dev-corp/inventory.yaml
View file

@ -1,6 +1,6 @@
test_env: dev-corp
profile: dev-corp-provider-pool
last_updated_at: "2026-07-11"
last_updated_at: "2026-07-13"
source:
remote_runner:
@ -115,6 +115,96 @@ model:
default: enabled
strict_output_behavior: provider_pool_catalog_default_overrides_strict_disable
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
family: spark_ornith
model_id: ornith:35b
display_name: Ornith 1.0 35B FP8 Direct vLLM
api: openai-completions
route_policy: Spark Ornith endpoints are direct-only until the separate IOP connection step; do not add them to the dev-corp Edge/provider pool from this inventory entry alone.
upstream_model: deepreinforce-ai/Ornith-1.0-35B-FP8
upstream_url: https://huggingface.co/deepreinforce-ai/Ornith-1.0-35B-FP8
upstream_revision: 1ab57ce0b44950e498a88756f40ad1ed4d0f30ca
docker_image: vllm/vllm-openai:nightly-aarch64
docker_image_id: sha256:cd3e070f40f57d23cb1aaad139aad87b52abccd5c5b9f4539186605b94e0fb9d
vllm_version: 0.23.1rc1.dev1042+g8e981630c
common_runtime_args:
max_model_len: 262144
max_num_seqs: 4
dtype: bfloat16
enable_prefix_caching: true
enable_auto_tool_choice: true
tool_call_parser: qwen3_xml
reasoning_parser: qwen3
trust_remote_code: true
runner: generate
language_model_only_equivalent: runner_generate
endpoints:
spark01:
provider: dev-corp-spark01-ornith
endpoint: http://192.168.2.2:8003/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
host_port: 8003
container_port: 8000
gpu_memory_utilization: 0.46
gpu_memory_utilization_note: Document baseline 0.50 was attempted but failed while preserving Gemma4 8002 because startup free GPU memory 56.02GiB was below the 59.85GiB reservation; KV cache was reduced through gpu_memory_utilization only.
hf_home: /models/.cache/huggingface
host_model_root: /home/digitalcommerce_dgx_spark_01/Data/models
model_load_memory_gib: 34.9
gpu_kv_cache_tokens: 857365
max_concurrency_for_262144_token_requests: 3.27
verification:
gemma4_8002_health: passed
ornith_8003_health: passed
models_endpoint: ornith:35b
direct_chat_completion: passed
pi_direct_print: PI_SPARK01_ORNITH_OK
spark02:
provider: dev-corp-spark02-ornith
endpoint: http://192.168.2.4:8005/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
host_port: 8005
container_port: 8000
gpu_memory_utilization: 0.50
hf_home: /models/.cache/huggingface
host_model_root: /home/dplab/Data/models
cache_source: copied_from_spark01_ornith_hf_cache_after_slow_hf_download
model_load_memory_gib: 34.9
gpu_kv_cache_tokens: 1074276
max_concurrency_for_262144_token_requests: 4.10
north_runtime_status: stopped_2026_07_12_for_ornith_direct_memory_headroom
verification:
gemma4_8004_health: passed
ornith_8005_health: passed
models_endpoint: ornith:35b
direct_chat_completion: passed
pi_direct_print: PI_SPARK02_ORNITH_OK
pi_direct_profile:
observed_at: "2026-07-13"
config_scope: host_local_pi_agent
default_provider: dev-corp-spark01-ornith
default_model: ornith:35b
default_thinking_level: high
enabled_model_patterns:
- dev-corp-spark02-ornith/*
- dev-corp-spark01-ornith/*
- dev-corp-direct/**
- dev-corp-spark01/**
- dev-corp/*
providers:
dev-corp-spark01-ornith:
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
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"
config_scope: host_local_pi_agent
@ -143,6 +233,8 @@ model:
retry_provider_max_retries: 0
retry_provider_max_retry_delay_ms: 60000
enabled_model_patterns:
- dev-corp-spark02-ornith/*
- dev-corp-spark01-ornith/*
- dev-corp-direct/**
- dev-corp-spark01/**
- dev-corp/*
@ -200,6 +292,38 @@ model:
thinking_format: chat-template
chat_template_kwargs:
enable_thinking: thinking.enabled
dgx_spark_01_ornith_direct:
provider: dev-corp-spark01-ornith
default_provider: true
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
compat:
supports_strict_mode: true
supports_developer_role: false
supports_usage_in_streaming: false
supports_reasoning_effort: false
supports_store: false
max_tokens_field: max_tokens
requires_tool_result_name: true
requires_assistant_after_tool_result: true
dgx_spark_02_ornith_direct:
provider: dev-corp-spark02-ornith
default_provider: false
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
compat:
supports_strict_mode: true
supports_developer_role: false
supports_usage_in_streaming: false
supports_reasoning_effort: false
supports_store: false
max_tokens_field: max_tokens
requires_tool_result_name: true
requires_assistant_after_tool_result: true
runtime_parameter_alignment:
alignment_policy: Pi model parameters must be kept in sync with the dev-corp Edge model alias, provider served_model values, context/output limits, Gemma parser/template policy, and provider capacity/sequence limits. Do not optimize or debug Pi behavior from the endpoint URL alone.
common_requirements: