iop/agent-test/dev/inventory.yaml

605 lines
25 KiB
YAML

test_env: dev
profile: dev-runtime-provider-pool
last_updated_at: "2026-07-12"
source:
remote_runner:
ssh: toki@toki-labs.com
repo_root: /Users/toki/agent-work/iop-dev
clean_sync:
- git fetch origin main
- git reset --hard origin/main
- git clean -fd
dirty_policy: discard
edge:
id: edge-toki-labs-dev
config_path: build/dev-runtime/edge.yaml
control_plane_http: http://127.0.0.1:18001
control_plane_status_url: http://127.0.0.1:18001/edges/edge-toki-labs-dev/status
bootstrap_http_public: http://toki-labs.com:18082
openai_base_url_public: http://toki-labs.com:18083/v1
openai_base_url_runner: http://127.0.0.1:18083/v1
edge_node_tcp_public: toki-labs.com:18084
admin_addr_runner: 127.0.0.1:19093
build:
binaries:
edge: build/dev-runtime/bin/edge
node_macos: build/dev-runtime/bin/iop-node
node_linux_arm64: build/dev-runtime/bin/iop-node-linux-arm64
node_windows_amd64: build/dev-runtime/bin/iop-node-windows-amd64.exe
model:
alias: qwen3.6:35b
provider_capacity_total: 9
provider_capacity_status: verified_with_control_plane_provider_snapshots_2026_07_08
context_window: 262144
default_max_tokens: 32768
min_max_tokens: 32768
default_thinking_token_budget: 1024
reasoning_policy: bounded_thinking
agent_tooling_policy:
runtime_profile: qwen_specific
mac_vllm_mlx:
tool_call_parser: qwen
reasoning_parser: qwen3
default_chat_template_kwargs:
enable_thinking: true
gx10_vllm:
reasoning_parser: qwen3
default_chat_template_kwargs:
enable_thinking: true
tool_call_parser_status: validate tools[] non-stream and streaming responses before enabling this provider for Pi/Cline-style agent tool use
separation_note: do not copy dev-corp Gemma parser/template values such as tool_call_parser=gemma4, reasoning_parser=gemma4, or Gemma4 chat templates into Qwen providers
pi_agent_profile:
observed_at: "2026-07-09"
config_scope: host_local_pi_agent
config_dir: /config/.pi/agent
current_default_provider: iop
current_default_model: qwen3.6:35b
current_default_thinking_level: high
current_default_api: openai-completions
current_default_base_url: http://toki-labs.com:18083/v1
current_default_auth_header: true
api_key_value_tracked: false
endpoint_policy: current_default_base_url is the observed route for this host Pi profile, but optimization compatibility is determined by the Qwen3.6 model alias, context/output limits, reasoning policy, and provider runtime settings rather than by the endpoint literal alone.
pi_model_parameters:
provider: iop
model_id: qwen3.6:35b
display_name: IOP Qwen 3.6 35B
api: openai-completions
context_window: 262144
max_tokens: 32768
reasoning: true
thinking_level: high
expected_iop_thinking_token_budget: 1024
runtime_parameter_alignment:
alignment_policy: Pi model parameters must be kept in sync with the Edge model catalog and each provider runtime profile. Do not optimize or debug Pi behavior from the endpoint URL alone; verify the alias-to-served-model mapping, context window, max token budget, thinking/reasoning parser, chat template kwargs, and provider capacity/sequence limits together.
common_requirements:
model_alias: qwen3.6:35b
pi_context_window: 262144
edge_context_window: 262144
pi_max_tokens: 32768
edge_default_max_tokens: 32768
edge_min_max_tokens: 32768
pi_reasoning: true
edge_reasoning_policy: bounded_thinking
edge_default_thinking_token_budget: 1024
required_template_policy: Qwen providers keep default_chat_template_kwargs.enable_thinking=true
required_reasoning_parser: qwen3
engine_matrix:
gx10-vllm:
runtime_type: vllm
served_model: nvidia/Qwen3.6-35B-A3B-NVFP4
context_match: pi contextWindow 262144 maps to vLLM max_model_len 262144
output_budget_match: pi maxTokens 32768 maps to provider default_max_tokens 32768
thinking_match: pi reasoning=true and thinking_level=high map to reasoning_parser=qwen3, default_chat_template_kwargs.enable_thinking=true, and IOP thinking token budget 1024
concurrency_match: provider capacity 4 maps to runtime max_num_seqs 4
tool_parser_profile: qwen3_xml
mac-mlx-vllm:
runtime_type: vllm-mlx
served_model: mlx-community/Qwen3.6-35B-A3B-4bit
context_match: pi contextWindow 262144 maps to vLLM-MLX max_request_tokens 262144 and max_kv_size 262144
output_budget_match: pi maxTokens 32768 maps to provider default_max_tokens 32768
thinking_match: pi reasoning=true and thinking_level=high map to reasoning_parser=qwen3, default_chat_template_kwargs.enable_thinking=true, and IOP thinking token budget 1024
concurrency_match: provider capacity 2 maps to runtime max_num_seqs 2
tool_parser_profile: qwen
onexplayer-lemonade:
runtime_type: lemonade
served_model: Qwen3.6-35B-A3B-MTP-GGUF
context_match: pi contextWindow 262144 is admitted within Lemonade ctx_size 524288 and current slot n_ctx 174848 x 3; long_context_capacity remains 2
output_budget_match: pi maxTokens 32768 maps to load default_max_tokens 32768
thinking_match: pi reasoning=true and thinking_level=high map to IOP bounded thinking budget 1024; Lemonade load keeps MTP disabled and tool_choice_auto_verified=true
concurrency_match: provider capacity 3 maps to Lemonade -np 3
tool_parser_profile: lemonade_qwen_tool_choice_auto_verified
separation_note: These alignment rules are for the dev Qwen3.6 provider pool only. Gemma4 and DiffusionGemma use separate provider/model profiles and must not inherit Qwen parser/template/context assumptions.
response_mode:
default: pure_passthrough
selector: metadata.iop_response_mode omitted or passthrough
verification: Chat Completions streaming probe returned HTTP 200 with no X-IOP-Response-Mode header and no iop.sideband marker; the same endpoint with metadata.iop_response_mode=passthrough+sideband returned X-IOP-Response-Mode=passthrough+sideband and iop.sideband, confirming mode separation.
provider_pool_routing:
observed_at: "2026-07-09"
caller_shape: Pi-compatible OpenAI Chat Completions streaming requests to provider/model iop/qwen3.6:35b
concurrent_requests: 10
peak_total_in_flight: 9
peak_total_queued_snapshot_units: 3
final_recovery: in_flight_0_queued_0
provider_peaks:
gx10-vllm:
runtime_type: vllm
served_model: nvidia/Qwen3.6-35B-A3B-NVFP4
capacity: 4
max_in_flight: 4
max_queued: 1
mac-mlx-vllm:
runtime_type: vllm-mlx
served_model: mlx-community/Qwen3.6-35B-A3B-4bit
capacity: 2
max_in_flight: 2
max_queued: 1
onexplayer-lemonade:
runtime_type: lemonade
served_model: Qwen3.6-35B-A3B-MTP-GGUF
capacity: 3
max_in_flight: 3
max_queued: 1
non_default_local_provider:
provider: iop-gemma
status: separate_direct_provider_not_part_of_dev_qwen_provider_pool
api: openai-completions
base_url: http://192.168.0.91:8002/v1
served_model: nvidia/diffusiongemma-26B-A4B-it-NVFP4
reasoning: false
current_runtime_status: stopped_2026_07_12_replaced_by_ornith_direct_fp8
spark_ornith_direct_profile:
observed_at: "2026-07-12"
provider: ornith-direct
status: active_direct_pi_provider_not_part_of_iop_provider_pool
family: spark_ornith
api: openai-completions
base_url: http://192.168.0.91:8002/v1
model_id: ornith:35b
display_name: Ornith 1.0 35B FP8 Direct vLLM
context_window: 262144
max_tokens: 32768
reasoning: true
endpoint_policy: Pi connects directly to the GX10/Spark vLLM OpenAI-compatible endpoint; this profile bypasses IOP Edge routing and does not participate in the dev Qwen provider pool.
api_key_value_tracked: false
pi_current_default_at_observation:
default_provider: ornith-direct
default_model: ornith:35b
default_api: openai-completions
default_base_url: http://192.168.0.91:8002/v1
qwen_parameter_alignment:
pi_context_window: 262144
pi_max_tokens: 32768
context_match: matches the dev Qwen Pi contextWindow and vLLM max_model_len value
output_budget_match: matches the dev Qwen Pi maxTokens/default_max_tokens value
runtime_summary:
host: toki@192.168.0.91
container_name: iop-vllm-ornith35b-fp8
docker_image: vllm/vllm-openai:nightly-aarch64
docker_image_id: sha256:a720df3e84a89d7db47a3b7a0511cb5b312e203fc4956f7493df248299267a6f
vllm_image_tag_env: vllm/vllm-openai:nightly-a346d589f5932d4234bf5bf8718f10e26d187021
vllm_version: 0.23.1rc1.dev223+ga346d589f
vllm_build_commit: a346d589f5932d4234bf5bf8718f10e26d187021
vllm_build_url: https://buildkite.com/vllm/release-v2/builds/2923
torch_version: 2.11.0+cu130
transformers_version: 5.12.1
compressed_tensors_version: 0.17.0
flashinfer_python_version: 0.6.12
cuda_version_env: 13.0.2
gpu: NVIDIA GB10
nvidia_driver_version: 580.126.09
endpoint: http://192.168.0.91:8002/v1
hf_model: deepreinforce-ai/Ornith-1.0-35B-FP8
hf_url: https://huggingface.co/deepreinforce-ai/Ornith-1.0-35B-FP8
hf_revision: 1ab57ce0b44950e498a88756f40ad1ed4d0f30ca
hf_ref: main
revision_argument: not_set_uses_repo_default_main_at_container_start
tokenizer_revision_argument: not_set_uses_model_revision
hf_home: /models/.cache/huggingface
hf_cache_snapshot_path: /models/.cache/huggingface/hub/models--deepreinforce-ai--Ornith-1.0-35B-FP8/snapshots/1ab57ce0b44950e498a88756f40ad1ed4d0f30ca
served_model_name: ornith:35b
openai_models_root: deepreinforce-ai/Ornith-1.0-35B-FP8
openai_models_max_model_len: 262144
quantization: fp8
vllm_quantization_backend: compressed-tensors
model_type: qwen3_5_moe
model_architecture: Qwen3_5MoeForConditionalGeneration
quantization_config_source: model config.json compressed-tensors W8A8 FP8, weight channel strategy, input activation token strategy, linear_attn/embed/lm_head/shared gates ignored
dtype: bfloat16
max_model_len: 262144
max_num_seqs: 2
max_num_batched_tokens: vllm_default_not_overridden
gpu_memory_utilization: 0.50
enable_prefix_caching: true
enable_chunked_prefill: true
async_scheduling: true
tensor_parallel_size: 1
pipeline_parallel_size: 1
data_parallel_size: 1
load_format: auto
download_dir: null
kv_cache_dtype: auto
enforce_eager: false
seed: 0
enable_auto_tool_choice: true
tool_call_parser: qwen3_xml
reasoning_parser: qwen3
reasoning_parser_enable_in_reasoning: false
trust_remote_code: true
language_model_only: true
attention_backend: FLASH_ATTN
sampling_backend: FlashInfer top-p/top-k
fp8_linear_kernel: CutlassFP8ScaledMMLinearKernel for CompressedTensorsW8A8Fp8
fp8_moe_backend: TRITON
generation_config_override:
temperature: 1.0
top_k: 20
top_p: 0.95
eos_token_id:
- 248046
- 248044
bos_token_id: 248044
docker_runtime:
created_at: "2026-07-12T04:40:26.013681328Z"
entrypoint:
- vllm
- serve
container_port: 8000
host_port: 8002
network_mode: bridge
ipc_mode: private
shm_size_bytes: 67108864
restart_policy: "no"
gpu_device_request: all
bind_mounts:
/home/toki/Data/models: /models
/home/toki/Data/vllm/templates: /templates
model_load_memory_gib: 34.43
model_load_seconds: 611.880026
weight_download_seconds: 407.868734
cuda_graph_memory_estimated_gib: 0.13
cuda_graph_pool_memory_actual_gib: 0.07
available_kv_cache_memory_gib: 21.33
gpu_kv_cache_tokens: 1087640
max_concurrency_for_262144_token_requests: 4.15
startup_warnings:
- vLLM command does not pin --revision; the recorded hf_revision is the downloaded snapshot observed in cache.
- Prefix caching in Mamba cache align mode is experimental for this architecture.
- Default MoE config for NVIDIA_GB10 FP8 was not found; vLLM used default MoE config, which may affect performance.
- Model generation_config overrides vLLM defaults unless callers provide sampling params or vLLM is relaunched with --generation-config vllm.
official_4bit_gguf_status:
hf_model: deepreinforce-ai/Ornith-1.0-35B-GGUF
hf_url: https://huggingface.co/deepreinforce-ai/Ornith-1.0-35B-GGUF
hf_revision: c2e1703039380de4ce6820e97afd185682d3c16c
hf_ref: main
hf_cache_snapshot_path: /models/.cache/huggingface/hub/models--deepreinforce-ai--Ornith-1.0-35B-GGUF/snapshots/c2e1703039380de4ce6820e97afd185682d3c16c
file: ornith-1.0-35b-Q4_K_M.gguf
status: not_active
reason: current vLLM GGUF plugin path exposed /v1/models but failed semantic generation smoke; active working runtime uses the official FP8 vLLM model instead.
smoke:
english_final_answer: passed
korean_final_answer: passed
pi_direct_cli: passed
output_throughput:
method: completion_tokens divided by end-to-end request wall time, max_tokens=768
average_completion_tok_s: 29.8
run_completion_tok_s:
- 29.65
- 30.62
- 29.15
note: vLLM logs showed aggregate generation throughput around 50-61 tok/s with two running requests.
separation_note: This host Pi default profile is the dev Qwen3.6 provider-pool profile. Keep dev-corp Gemma4 under agent-test/dev-corp/inventory.yaml and do not copy Gemma4 parser/template/runtime settings into this Qwen profile.
content_completion_policy:
enforce_min_max_tokens: true
reason: prevent reasoning-only completions from exhausting caller max_tokens before final content
dispatch_policy:
capacity_gate: providers at or above capacity are excluded from dispatch candidates
selection_order: lower in_flight level wins among providers with available capacity
same_in_flight_tiebreak: lower numeric priority first, then deterministic rotation
capacity_smoke:
endpoints:
- /v1/responses
- /v1/chat/completions
concurrent_requests: 9
expected_total_in_flight: 9
expected_min_queued: 0
capacity_plus_one_concurrent_requests: 10
capacity_plus_one_expected_total_in_flight: 9
capacity_plus_one_expected_min_queued: 1
extended_concurrent_requests: 13
extended_expected_min_queued: 4
prompt_policy: long_reasoning_allowed
exact_output_match: false
latest_provider_snapshot:
observed_at: "2026-07-08"
total_capacity: 9
all_nodes_connected: true
providers:
gx10-vllm:
capacity: 4
priority: 0
in_flight: 0
queued: 0
health: healthy
served_model: nvidia/Qwen3.6-35B-A3B-NVFP4
mac-mlx-vllm:
capacity: 2
priority: 2
in_flight: 0
queued: 0
health: healthy
served_model: mlx-community/Qwen3.6-35B-A3B-4bit
onexplayer-lemonade:
capacity: 3
priority: 1
in_flight: 0
queued: 0
health: healthy
served_model: Qwen3.6-35B-A3B-MTP-GGUF
openai_tool_call_smoke:
observed_at: "2026-07-08"
request_shape: tools_plus_tool_choice_auto
direct_provider_expected:
http_status: 200
minimum_tool_calls: 1
direct_provider_result:
gx10-vllm:
http_status: 200
tool_calls: 1
mac-mlx-vllm:
http_status: 200
tool_calls: 1
onexplayer-lemonade:
http_status: 200
tool_calls: 1
edge_concurrency_result:
endpoint: /v1/chat/completions
concurrent_requests: 10
success_count: 10
failure_count: 0
tool_call_response_count: 10
finish_reason_tool_calls: 10
peak_total_in_flight: 9
peak_total_queued: 3
provider_result_counts:
gx10-vllm: 5
onexplayer-lemonade: 3
mac-mlx-vllm: 2
provider_peaks:
gx10-vllm:
max_in_flight: 4
max_queued: 1
onexplayer-lemonade:
max_in_flight: 3
max_queued: 1
mac-mlx-vllm:
max_in_flight: 2
max_queued: 1
final_content_smoke:
endpoint: /v1/chat/completions
concurrent_requests: 10
current_capacity_total: 9
expected_peak_total_in_flight: 9
expected_min_queued: 1
request_max_tokens: 3072
effective_min_max_tokens: 32768
include_reasoning: false
expected_success_count: 10
expected_finish_reason: stop
expected_final_marker: true
expected_empty_content: 0
expected_iop_notice: 0
previous_observed_at: "2026-07-04"
previous_observed_capacity_total: 10
previous_observed_result:
http_ok: 10
success_count: 10
failure_count: 0
finish_reason_stop: 10
marker_missing_count: 0
empty_content_count: 0
iop_notice_count: 0
think_tag_leak_count: 0
reasoning_present_count: 0
aggregate_completion_tok_s: 62.5
total_completion_tokens: 17933
batch_wall_sec: 286.908
avg_latency_sec: 175.074
peak_total_in_flight: 10
peak_total_queued: 0
provider_peaks:
gx10-vllm:
capacity: 4
max_in_flight: 4
max_queued: 0
mac-mlx-vllm:
capacity: 3
max_in_flight: 3
max_queued: 0
onexplayer-lemonade:
capacity: 3
max_in_flight: 3
max_queued: 0
nodes:
- id: mac-codex-node
alias: mac-codex
role: cli+mlx-provider
ssh: toki@toki-labs.com
workspace: /Users/toki/agent-work/iop-workspace/nomadcode
provider_pool_candidate: true
adapters:
- cli
- mac-mlx-vllm
providers:
- id: mac-mlx-vllm
type: vllm-mlx
endpoint: http://127.0.0.1:8002/v1
served_model: mlx-community/Qwen3.6-35B-A3B-4bit
capacity: 2
priority: 2
# Long-context admission policy (maps to edge.yaml nodes[].providers[]).
# Runtime KV budget is 262144 (max_kv_size / max_request_tokens), so only
# one full 262144-window long request fits. long_context_capacity is the
# long-slot count, distinct from the normal capacity (2).
total_context_tokens: 262144
long_context_capacity: 1
runtime:
api_key_policy: local_bearer_from_edge_yaml
workdir: /Users/toki/agent-work/iop-mlx-vllm
python: .venv/bin/python
package_baseline:
vllm_mlx: 0.3.0
mlx: 0.31.2
mlx_lm: 0.31.3
model_cache: /Users/toki/agent-work/iop-mlx-vllm/hf-cache
pid_file: /Users/toki/agent-work/iop-mlx-vllm/vllm-mlx.pid
stdout_log: /Users/toki/agent-work/iop-mlx-vllm/logs/vllm-mlx.stdout.log
stderr_log: /Users/toki/agent-work/iop-mlx-vllm/logs/vllm-mlx.stderr.log
max_num_seqs: 2
max_kv_size: 262144
max_request_tokens: 262144
default_max_tokens: 32768
default_thinking_token_budget: 1024
paged_cache_block_size: 64
max_cache_blocks: 4096
total_kv_tokens: 262144
enable_auto_tool_choice: true
tool_call_parser: qwen
reasoning_parser: qwen3
default_chat_template_kwargs:
enable_thinking: true
- id: gx10-vllm-node
alias: gx10-vllm
role: vllm-provider
ssh: toki@192.168.0.91
workspace: /home/toki/iop-gx10-vllm
provider_pool_candidate: true
provider:
id: gx10-vllm
type: vllm
endpoint: http://192.168.0.91:8001/v1
served_model: nvidia/Qwen3.6-35B-A3B-NVFP4
capacity: 4
priority: 0
# Long-context admission policy (maps to edge.yaml nodes[].providers[]).
# max_model_len is 262144; conservative long_context_capacity=1 until runtime
# evidence proves a larger concurrent long-context KV budget.
total_context_tokens: 262144
long_context_capacity: 1
runtime:
container_name: iop-vllm-qwen36-prev-20260704063128
max_model_len: 262144
max_num_seqs: 4
gpu_memory_utilization: 0.30
default_max_tokens: 32768
default_thinking_token_budget: 1024
enable_auto_tool_choice: true
tool_call_parser: qwen3_xml
reasoning_parser: qwen3
default_chat_template_kwargs:
enable_thinking: true
direct_providers:
- id: ornith-direct
family: spark_ornith
type: vllm
endpoint: http://192.168.0.91:8002/v1
served_model: ornith:35b
upstream_model: deepreinforce-ai/Ornith-1.0-35B-FP8
upstream_url: https://huggingface.co/deepreinforce-ai/Ornith-1.0-35B-FP8
upstream_revision: 1ab57ce0b44950e498a88756f40ad1ed4d0f30ca
status: active_direct_pi_provider_not_iop_routed
pi_model_parameters:
context_window: 262144
max_tokens: 32768
reasoning: true
runtime:
container_name: iop-vllm-ornith35b-fp8
docker_image: vllm/vllm-openai:nightly-aarch64
docker_image_id: sha256:a720df3e84a89d7db47a3b7a0511cb5b312e203fc4956f7493df248299267a6f
vllm_version: 0.23.1rc1.dev223+ga346d589f
vllm_build_commit: a346d589f5932d4234bf5bf8718f10e26d187021
port_mapping: 0.0.0.0:8002->8000
hf_home: /models/.cache/huggingface
hf_cache_snapshot_path: /models/.cache/huggingface/hub/models--deepreinforce-ai--Ornith-1.0-35B-FP8/snapshots/1ab57ce0b44950e498a88756f40ad1ed4d0f30ca
quantization: fp8
vllm_quantization_backend: compressed-tensors
dtype: bfloat16
max_model_len: 262144
max_num_seqs: 2
max_num_batched_tokens: vllm_default_not_overridden
gpu_memory_utilization: 0.50
enable_prefix_caching: true
enable_chunked_prefill: true
async_scheduling: true
tensor_parallel_size: 1
pipeline_parallel_size: 1
data_parallel_size: 1
load_format: auto
download_dir: null
kv_cache_dtype: auto
enforce_eager: false
enable_auto_tool_choice: true
tool_call_parser: qwen3_xml
reasoning_parser: qwen3
reasoning_parser_enable_in_reasoning: false
trust_remote_code: true
language_model_only: true
attention_backend: FLASH_ATTN
fp8_linear_kernel: CutlassFP8ScaledMMLinearKernel for CompressedTensorsW8A8Fp8
fp8_moe_backend: TRITON
generation_config_override:
temperature: 1.0
top_k: 20
top_p: 0.95
docker_runtime:
network_mode: bridge
ipc_mode: private
shm_size_bytes: 67108864
restart_policy: "no"
gpu_device_request: all
bind_mounts:
/home/toki/Data/models: /models
/home/toki/Data/vllm/templates: /templates
model_load_memory_gib: 34.43
available_kv_cache_memory_gib: 21.33
gpu_kv_cache_tokens: 1087640
max_concurrency_for_262144_token_requests: 4.15
average_completion_tok_s: 29.8
replacement_note: DiffusionGemma direct vLLM on this endpoint was stopped; Ornith is served from the official FP8 Hugging Face release, not the 4-bit GGUF build.
- id: onexplayer-lemonade-node
alias: onexplayer-lemonade
role: lemonade-provider
ssh: r0bin@192.168.0.59
ssh_origin: current_host
workspace: C:/Users/r0bin/iop-field
provider_pool_candidate: true
provider:
id: onexplayer-lemonade
type: lemonade
endpoint: http://192.168.0.59:13305/v1
served_model: Qwen3.6-35B-A3B-MTP-GGUF
capacity: 3
priority: 1
# Long-context admission policy (maps to edge.yaml nodes[].providers[]).
# SDD D04 fixes OneXPlayer dev baseline at ctx_size=524288, -np 3,
# long_context_capacity=2. Do NOT raise ctx_size above 524288.
total_context_tokens: 524288
long_context_capacity: 2
load:
endpoint: http://192.168.0.59:13305/v1/load
model_name: Qwen3.6-35B-A3B-MTP-GGUF
backend: vulkan
ctx_size: 524288
llamacpp_args: "--spec-type none -np 3 -cb -fa on -b 4096 -ub 1024"
observed_slot_n_ctx: 174848
save_options: true
mtp_runtime_policy: disabled
default_max_tokens: 32768
default_thinking_token_budget: 1024
tool_choice_auto_verified: true
windows_process_start: Win32_Process.Create