toki/iop
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
iop/agent-test/dev-corp/inventory.yaml
toki d6dd3da59d docs(dev-corp): Control Plane 검증 기준을 갱신한다 
native Control Plane이 활성화된 provider-pool 상태와 capacity smoke 결과를 dev-corp 테스트 규칙과 인벤토리에 반영한다.
2026-07-02 16:07:26 +09:00

330 lines
14 KiB
YAML
Raw Blame History

test_env: dev-corp
profile: dev-corp-provider-pool
last_updated_at: "2026-07-02"
source:
remote_runner:
ssh: fe@172.24.63.178
repo_root: /Users/fe/agent-work/iop-dev-corp
setup_required: true
setup_status: deployed
current_observation: /Users/fe/agent-work/iop-dev-corp checkout and build/dev-corp-runtime runtime were created on 2026-06-25, then clean-synced/rebuilt at source ref 5b1255a on 2026-07-02; /Users/fe/iop-field remains unrelated legacy field state
clean_sync:
- git fetch origin main
- git reset --hard origin/main
- git clean -fd
dirty_policy: discard
edge:
id: dev-corp-edge
host: mac-mini
ssh: fe@172.24.63.178
os: macOS 26.2
hardware: Apple M2 Pro / 16GB
config_path: build/dev-corp-runtime/edge.yaml
control_plane_enabled_current_runtime: true
control_plane_http: http://127.0.0.1:18002
control_plane_status_url: http://127.0.0.1:18002/edges/dev-corp-edge/status
control_plane_client_ws_runner: ws://127.0.0.1:19004/client
control_plane_edge_wire_addr_runner: 127.0.0.1:19005
bootstrap_http_public: http://172.24.63.178:18085
openai_base_url_public: http://172.24.63.178:18086/v1
openai_base_url_runner: http://127.0.0.1:18086/v1
openai_api_key_required_current_runtime: true
openai_api_key_secret_path_remote: build/dev-corp-runtime/.secrets/openai_api_key
openai_api_key_value_tracked: false
edge_node_tcp_public: 172.24.63.178:18087
admin_addr_runner: 127.0.0.1:19094
build:
binaries:
control_plane: build/dev-corp-runtime/bin/control-plane
edge: build/dev-corp-runtime/bin/iop-edge
node_macos: build/dev-corp-runtime/bin/iop-node-darwin-arm64
node_linux_arm64: build/dev-corp-runtime/bin/iop-node-linux-arm64
node_windows_amd64: null
node_windows_amd64_note: not part of the default dev-corp provider pool
model:
alias: gemma4:26b
alias_status: candidate
alias_policy: expose one IOP model alias and map provider-specific served_model values per provider
provider_capacity_total: 13
provider_capacity_status: verified_with_control_plane_provider_snapshots_2026_07_02
context_window_max: 262144
runtime_capacity_targets:
dgx_spark:
capacity: 4
context_window_max: 262144
kv_size_tokens_effective: 524288
kv_size_basis: requested minimum 262144x2; verify actual vLLM KV cache from startup log because gpu_memory_utilization controls available KV cache
fp4_moe_env: VLLM_MAX_TOKENS_PER_EXPERT_FP4_MOE=4194304
mac_studio:
capacity: 5
context_window_max: 262144
kv_size_tokens_effective: 786432
kv_size_basis: requested 262144x3 mapped to vLLM-MLX max_kv_size
capacity_smoke:
endpoints:
- /v1/responses
- /v1/chat/completions
concurrent_requests: capacity_plus_one
expected_total_in_flight: 13
expected_total_in_flight_status: verified_2026_07_02
expected_min_queued: 1
extended_concurrent_requests: 16
extended_expected_min_queued: 3
prompt_policy: long_reasoning_allowed
exact_output_match: false
latest_capacity_verification:
date: "2026-07-02"
source_ref: 5b1255abc5ad530ebfd7a65deecdf5575425a34c
control_plane_enabled: true
control_plane_status_url: http://127.0.0.1:18002/edges/dev-corp-edge/status
provider_snapshot_baseline:
total_capacity: 13
providers:
corp-dgx-spark-01-vllm:
capacity: 4
health: healthy
status: available
corp-dgx-spark-02-vllm:
capacity: 4
health: healthy
status: available
corp-mac-studio-mlx-vllm:
capacity: 5
health: healthy
status: available
responses:
concurrent_requests: 14
ok: 14
max_total_in_flight: 13
max_total_queued: 3
provider_max:
corp-dgx-spark-01-vllm:
max_in_flight: 4
max_queued: 1
corp-dgx-spark-02-vllm:
max_in_flight: 4
max_queued: 1
corp-mac-studio-mlx-vllm:
max_in_flight: 5
max_queued: 1
final_recovery: in_flight_0_queued_0
chat_completions:
concurrent_requests: 14
ok: 14
max_total_in_flight: 13
max_total_queued: 3
provider_max:
corp-dgx-spark-01-vllm:
max_in_flight: 4
max_queued: 1
corp-dgx-spark-02-vllm:
max_in_flight: 4
max_queued: 1
corp-mac-studio-mlx-vllm:
max_in_flight: 5
max_queued: 1
final_recovery: in_flight_0_queued_0
latest_runtime_update:
date: "2026-06-25"
reason: user requested dev-corp node capacity/context/KV alignment
requested_targets:
dgx_spark:
capacity: 4
context_window_max: 262144
kv_size: 262144x2
mac_studio:
capacity: 5
context_window_max: 262144
kv_size: 262144x3
applied_mapping:
dgx_spark: vLLM has no vLLM-MLX style max_kv_size flag; requested KV 262144x2 is validated from startup log KV cache size and max_model_len 262144
mac_studio: vLLM-MLX requested KV 262144x3 is represented as max_kv_size 786432 with max_request_tokens 262144
remediation_applied:
- DGX Spark vLLM FP4 MoE first profile required VLLM_MAX_TOKENS_PER_EXPERT_FP4_MOE=4194304 for max_num_batched_tokens 524288
- DGX Spark 01 FlashInfer FP4 JIT invokes ninja from PATH; start script now prefixes /home/digitalcommerce_dgx_spark_01/vllm_env/bin
- Mac Studio vLLM-MLX pyexpat required DYLD_LIBRARY_PATH=/opt/homebrew/opt/expat/lib
verification:
last_rechecked_at: "2026-07-02"
mac_studio_health: passed
dgx01_health: passed
dgx02_health: passed
direct_health_observation:
dgx01: mac-mini http://192.168.2.2:8002 returned /health 200 and /v1/models exposed gemma-4-26B-A4B-it-NVFP4 after vllm_server_8002 restart; startup log reported GPU KV cache size 834,507 tokens and 3.18x concurrency for 262,144-token requests
dgx02: node-local http://127.0.0.1:8004 and mac-mini http://192.168.2.4:8004 returned /health 200, /v1/models exposed gemma-4-26B-A4B-it-NVFP4, and direct concurrency 1..4 chat completion benchmark passed
mac_studio: node-local http://127.0.0.1:8004 and mac-mini http://192.168.2.3:8004 returned /health 200, /v1/models exposed mlx-community/gemma-4-26b-a4b-it-nvfp4, and direct concurrency 1..5 chat completion benchmark passed
edge_openai_smoke: passed_with_control_plane_capacity_snapshot_2026_07_02
nodes:
- id: corp-dgx-spark-01-vllm-node
alias: corp-dgx-spark-01-vllm
role: vllm-provider
ssh: digitalcommerce_dgx_spark_01@192.168.2.2
ssh_origin: mac-mini
workspace: /home/digitalcommerce_dgx_spark_01
provider_pool_candidate: true
provider:
id: corp-dgx-spark-01-vllm
type: vllm
endpoint: http://192.168.2.2:8002/v1
edge_adapter_endpoint: http://127.0.0.1:8002/v1
health: http://192.168.2.2:8002/health
served_model: gemma-4-26B-A4B-it-NVFP4
capacity: 4
capacity_status: configured_health_passed_direct_smoke_and_edge_capacity_smoke
last_runtime_observation: restarted with gpu_memory_utilization 0.40 on 2026-07-02; mac-mini http://192.168.2.2:8002 returned /health 200 and /v1/models; startup log reported GPU KV cache size 834,507 tokens and 3.18x concurrency for 262,144-token requests
capacity_basis: dev-corp target baseline; vLLM --max-num-seqs 4, --max-model-len 262144, --gpu-memory-utilization 0.40; observed KV cache satisfies requested 262144x2 minimum
edge_connectivity:
mode: reverse_ssh_tunnel
reason: current node.yaml uses tunnel-local Edge addr in the native provider-pool runtime
tunnel_pid_file: /Users/fe/agent-work/iop-dev-corp/build/dev-corp-runtime/node01-tunnel.pid
remote_forwards:
artifact: 127.0.0.1:28085 -> mac-mini 127.0.0.1:18085
edge_node_tcp: 127.0.0.1:28087 -> mac-mini 127.0.0.1:18087
runtime:
host: spark-0b30
os: Ubuntu 24.04.3 LTS / aarch64
hardware: NVIDIA DGX Spark / NVIDIA GB10 / 119GiB RAM
manager: tmux
tmux_session: vllm_server_8002
start_script: /home/digitalcommerce_dgx_spark_01/start_vllm_8002.sh
python: /home/digitalcommerce_dgx_spark_01/vllm_env/bin/python3
path_prefix_required: /home/digitalcommerce_dgx_spark_01/vllm_env/bin
path_prefix_reason: FlashInfer FP4 JIT invokes ninja from PATH during first compile
package_baseline:
vllm: 0.23.0
torch: 2.11.0
transformers: 5.12.1
flashinfer_python: 0.6.12
huggingface_hub: 1.20.1
args:
env:
PATH_prefix: /home/digitalcommerce_dgx_spark_01/vllm_env/bin
VLLM_MAX_TOKENS_PER_EXPERT_FP4_MOE: "4194304"
host: 0.0.0.0
port: 8002
dtype: bfloat16
gpu_memory_utilization: 0.40
max_model_len: 262144
max_num_seqs: 4
max_num_batched_tokens: auto_2496
max_num_batched_tokens_note: vLLM raised the default from 2048 to 2496 for the Gemma4 prefix-LM/video path; it is a scheduler iteration budget, not the total KV cache size
context_window_max: 262144
kv_size_tokens_effective: 834507
full_context_concurrency_observed: 3.18
- id: corp-dgx-spark-02-vllm-node
alias: corp-dgx-spark-02-vllm
role: vllm-provider
ssh: dplab@192.168.2.4
ssh_origin: mac-mini
workspace: /home/dplab
provider_pool_candidate: true
provider:
id: corp-dgx-spark-02-vllm
type: vllm
endpoint: http://192.168.2.4:8004/v1
edge_adapter_endpoint: http://127.0.0.1:8004/v1
health: http://192.168.2.4:8004/health
served_model: gemma-4-26B-A4B-it-NVFP4
capacity: 4
capacity_status: configured_health_passed_direct_smoke_and_edge_capacity_smoke
last_runtime_observation: Docker vllm-gemma4 running with gpu_memory_utilization 0.40; node-local and mac-mini /health passed, /v1/models exposed gemma-4-26B-A4B-it-NVFP4, and direct concurrency 1..4 chat completion benchmark passed; startup log reported GPU KV cache size 860,222 tokens and 3.28x concurrency for 262,144-token requests
capacity_basis: dev-corp target baseline; Docker publishes host 8004 to container 8004; vLLM --max-num-seqs 4, --max-model-len 262144, --gpu-memory-utilization 0.40; observed KV cache satisfies requested 262144x2 minimum
edge_connectivity:
mode: reverse_ssh_tunnel
reason: node02 cannot reach mac-mini 172.24.63.178:18085/18086 directly from 192.168.2.4
tunnel_pid_file: /Users/fe/agent-work/iop-dev-corp/build/dev-corp-runtime/node02-tunnel.pid
remote_forwards:
artifact: 127.0.0.1:28085 -> mac-mini 127.0.0.1:18085
edge_node_tcp: 127.0.0.1:28087 -> mac-mini 127.0.0.1:18087
runtime:
host: spark-fb94
os: Ubuntu 24.04.3 LTS / aarch64
hardware: NVIDIA DGX Spark / NVIDIA GB10 / 119GiB RAM
manager: docker
container_name: vllm-gemma4
start_script: /home/dplab/start_vllm_gemma4_8004.sh
env_file: /home/dplab/.config/iop-dev-corp/vllm-gemma4.env
env_file_contains_secret: true
image: vllm/vllm-openai:latest
container_port: 8004
host_port: 8004
package_baseline:
vllm: 0.23.0
torch: 2.11.0+cu130
transformers: 5.12.0
flashinfer_python: 0.6.12
huggingface_hub: 1.19.0
args:
env:
VLLM_MAX_TOKENS_PER_EXPERT_FP4_MOE: "4194304"
gpu_memory_utilization: 0.40
max_model_len: 262144
max_num_seqs: 4
max_num_batched_tokens: auto_2496
max_num_batched_tokens_note: vLLM raised the default from 2048 to 2496 for the Gemma4 prefix-LM/video path; it is a scheduler iteration budget, not the total KV cache size
context_window_max: 262144
kv_size_tokens_effective: 860222
full_context_concurrency_observed: 3.28
- id: corp-mac-studio-mlx-vllm-node
alias: corp-mac-studio-mlx-vllm
role: vllm-mlx-provider
ssh: dc_dev@192.168.2.3
ssh_origin: mac-mini
workspace: /Users/dc_dev
provider_pool_candidate: true
provider:
id: corp-mac-studio-mlx-vllm
type: openai_compat
runtime_type: vllm-mlx
endpoint: http://192.168.2.3:8004/v1
edge_adapter_endpoint: http://127.0.0.1:8004/v1
health: http://192.168.2.3:8004/health
served_model: mlx-community/gemma-4-26b-a4b-it-nvfp4
capacity: 5
capacity_status: configured_health_passed_direct_smoke_and_edge_capacity_smoke
last_runtime_observation: screen vllm_mlx_8004 running with max_num_seqs 5, max_request_tokens 262144, max_kv_size 786432; node-local and mac-mini /health passed, /v1/models exposed mlx-community/gemma-4-26b-a4b-it-nvfp4, and direct concurrency 1..5 chat completion benchmark passed
capacity_basis: vllm-mlx --max-num-seqs 5 with requested KV 262144x3 mapped to --max-kv-size 786432
runtime:
host: dc-devui-MacStudio.local
os: macOS 26.2
hardware: Apple M3 Ultra / 512GB RAM / 80-core GPU
manager: screen
manager_status: detached screen session vllm_mlx_8004; DYLD_LIBRARY_PATH=/opt/homebrew/opt/expat/lib is required for pyexpat on this host
screen_session: vllm_mlx_8004
start_script: /Users/dc_dev/iop-dev-corp-field/start_vllm_mlx_8004.sh
python: /Users/dc_dev/vllm-env/bin/python
package_baseline:
vllm_mlx: 0.3.0
mlx: 0.31.2
mlx_lm: 0.31.3
mlx_vlm: 0.6.3
torch: 2.12.1
transformers: 5.12.1
huggingface_hub: 1.20.1
args:
host: 0.0.0.0
port: 8004
continuous_batching: true
max_num_seqs: 5
prefill_batch_size: 5
completion_batch_size: 5
chunked_prefill_tokens: 1024
max_kv_size: 786432
max_request_tokens: 262144
context_window_max: 262144
kv_size_tokens_effective: 786432
reasoning_parser: gemma4
secondary_provider_candidate:
id: corp-mac-studio-mlx-vlm-diffusiongemma
type: mlx-vlm
endpoint: http://192.168.2.3:8005/v1
health: http://192.168.2.3:8005/health
served_model: mlx-community/diffusiongemma-26B-A4B-it-OptiQ-4bit
include_in_default_pool: false
note: exposes multiple models and should be routed only after alias/capacity policy is decided
Reference in a new issue View git blame Copy permalink