# Phase A-prime runtime profile data (v0.8.0, club-3090 #359 / PR #147).
#
# WHY THIS FILE EXISTS (storage decision — documented in docs/PATCH_ATTRIBUTION.md):
#   The #141 generator (STEP 2/3) needs, per in-scope profile, the whole
#   shipped service definition classified into param / governed / constant
#   tokens plus the two patch insertion points, and a genesis discriminator.
#   It also needs an arch -> model-slug cross-reference and per-model
#   trust-remote-code precision. The Phase-A `arch_patches.yml` schema is a
#   STRICT closed key-set enforced by scripts/tests/test-patch-attribution.sh
#   (`arch_allowed_keys`); adding `model_slugs` directly there would trip the
#   "unknown keys" guard, and the test is the contract (RED-LINE: the test is
#   not editable in this commit). Therefore the Phase-A-prime fold-ins that
#   the brief scopes "onto arch rows" are stored HERE, keyed by the same
#   `arch:` string, so arch_patches.yml stays schema-clean and the existing
#   test stays green. profile_runtime.yml was chosen over COMPOSE_REGISTRY
#   fields because the captured templates are large structured blocks and the
#   registry is a thin param-value bridge that the test imports as a Python
#   module (keeping it data-thin avoids import-surface churn).
#
# GROUNDING DISCIPLINE: every value below was derived by reading the shipped
# compose at `compose_path` (verbatim) and each model's own config.json on
# this stack. Nothing is guessed. Values that could not be established from an
# artifact are written `unverified` / `none` and listed in the commit report.
schema_version: 1

# --------------------------------------------------------------------------
# Per-profile captured runtime template (in-scope vLLM profiles only).
#   genesis_equipped (locked v6 discriminator): true iff the shipped compose
#   contains _genesis / GENESIS_PIN / GENESIS_ENABLE OR kv_format starts with
#   'turboquant'. Computed by reading the compose, not by guessing.
#   compose_service_template: the WHOLE service definition is the captured
#   unit (file at `source`); this block records the token CLASSIFICATION the
#   generator applies (param-slot | governed-slot | constant) + the two named
#   insertion-point anchors. The `image:` expression is a captured CONSTANT
#   (correction #2 — never substituted). `--trust-remote-code` is a
#   GOVERNED-slot (correction #1 — never blind-passthrough).
# --------------------------------------------------------------------------
profiles:
  vllm/default:
    compose_path: models/qwen3.6-27b/vllm/compose/single/autoround-int4/tq3-mtp.yml
    genesis_equipped: true
    genesis_equipped_evidence: compose contains GENESIS_* / _genesis token
    compose_service_template:
      source: models/qwen3.6-27b/vllm/compose/single/autoround-int4/tq3-mtp.yml  # whole service definition captured verbatim from this file
      param_slots:
        ports: { source: E.default_port, value: 8020 }
        tensor_parallel_size: { token: '${TP}', source: E.tp, value: 1 }
        max_model_len: { token: '${MAX_MODEL_LEN}', source: E.max_ctx, value: 48000 }
        gpu_memory_utilization: { token: '${GPU_MEMORY_UTILIZATION}', source: E.mem_util, value: 0.92 }
        kv_cache_dtype: { token: '${KV_CACHE_DTYPE}', source: 'kv_arg(E.kv_format)', kv_format: turboquant_3bit_nc, value: 'turboquant_3bit_nc' }
        max_num_seqs: { token: '--max-num-seqs', source: E.max_num_seqs, value: 1 }
        speculative_config: { token: '--speculative-config', source: 'drafter[qwen-mtp-builtin].speculative_config_template' }
      governed_slots:
        trust_remote_code:
          token: '--trust-remote-code'
          present_in_shipped_compose: true
          policy: governed   # locked design v6 §88 security model
          emit_rule: 'only if arch trc gate resolves evidence-cited false-permitted; never blind-passthrough'
      constants:
        image: '${VLLM_IMAGE:-vllm/vllm-openai:nightly-${VLLM_NIGHTLY_SHA}}'   # captured constant; engine pin flows via env, NOT rewritten
        verbatim_from_compose: [shm_size, ipc, deploy.resources, model_cache_volume, base_environment, base_entrypoint, '--model', '--served-model-name', '--quantization', '--dtype', '--tool-call-parser', '--chat-template', '--reasoning-parser', '--default-chat-template-kwargs', '--enable-prefix-caching', '--enable-chunked-prefill', '--enforce-eager']
      insertion_points:
        volumes: present    # overlay/sidecar mount anchor
        entrypoint: present  # sidecar invoke anchor
  vllm/long-text:
    compose_path: models/qwen3.6-27b/vllm/compose/single/autoround-int4/long-text.yml
    genesis_equipped: true
    genesis_equipped_evidence: compose contains GENESIS_* / _genesis token
    compose_service_template:
      source: models/qwen3.6-27b/vllm/compose/single/autoround-int4/long-text.yml  # whole service definition captured verbatim from this file
      param_slots:
        ports: { source: E.default_port, value: 8020 }
        tensor_parallel_size: { token: '${TP}', source: E.tp, value: 1 }
        max_model_len: { token: '${MAX_MODEL_LEN}', source: E.max_ctx, value: 180000 }
        gpu_memory_utilization: { token: '${GPU_MEMORY_UTILIZATION}', source: E.mem_util, value: 0.93 }
        kv_cache_dtype: { token: '${KV_CACHE_DTYPE}', source: 'kv_arg(E.kv_format)', kv_format: turboquant_3bit_nc, value: 'turboquant_3bit_nc' }
        max_num_seqs: { token: '--max-num-seqs', source: E.max_num_seqs, value: 1 }
        speculative_config: { token: '--speculative-config', source: 'drafter[qwen-mtp-builtin].speculative_config_template' }
      governed_slots:
        trust_remote_code:
          token: '--trust-remote-code'
          present_in_shipped_compose: true
          policy: governed   # locked design v6 §88 security model
          emit_rule: 'only if arch trc gate resolves evidence-cited false-permitted; never blind-passthrough'
      constants:
        image: '${VLLM_IMAGE:-vllm/vllm-openai:nightly-${VLLM_NIGHTLY_SHA}}'   # captured constant; engine pin flows via env, NOT rewritten
        verbatim_from_compose: [shm_size, ipc, deploy.resources, model_cache_volume, base_environment, base_entrypoint, '--model', '--served-model-name', '--quantization', '--dtype', '--tool-call-parser', '--chat-template', '--reasoning-parser', '--default-chat-template-kwargs', '--enable-prefix-caching', '--enable-chunked-prefill', '--enforce-eager']
      insertion_points:
        volumes: present    # overlay/sidecar mount anchor
        entrypoint: present  # sidecar invoke anchor
  vllm/long-text-no-mtp:
    compose_path: models/qwen3.6-27b/vllm/compose/single/autoround-int4/long-text-no-mtp.yml
    genesis_equipped: true
    genesis_equipped_evidence: compose contains GENESIS_* / _genesis token
    compose_service_template:
      source: models/qwen3.6-27b/vllm/compose/single/autoround-int4/long-text-no-mtp.yml  # whole service definition captured verbatim from this file
      param_slots:
        ports: { source: E.default_port, value: 8021 }
        tensor_parallel_size: { token: '${TP}', source: E.tp, value: 1 }
        max_model_len: { token: '${MAX_MODEL_LEN}', source: E.max_ctx, value: 200000 }
        gpu_memory_utilization: { token: '${GPU_MEMORY_UTILIZATION}', source: E.mem_util, value: 0.95 }
        kv_cache_dtype: { token: '${KV_CACHE_DTYPE}', source: 'kv_arg(E.kv_format)', kv_format: turboquant_3bit_nc, value: 'turboquant_3bit_nc' }
        max_num_seqs: { token: '--max-num-seqs', source: E.max_num_seqs, value: 1 }
        speculative_config: omitted  # E.drafter is None -> --speculative-config not emitted
      governed_slots:
        trust_remote_code:
          token: '--trust-remote-code'
          present_in_shipped_compose: true
          policy: governed   # locked design v6 §88 security model
          emit_rule: 'only if arch trc gate resolves evidence-cited false-permitted; never blind-passthrough'
      constants:
        image: '${VLLM_IMAGE:-vllm/vllm-openai:nightly-${VLLM_NIGHTLY_SHA}}'   # captured constant; engine pin flows via env, NOT rewritten
        verbatim_from_compose: [shm_size, ipc, deploy.resources, model_cache_volume, base_environment, base_entrypoint, '--model', '--served-model-name', '--quantization', '--dtype', '--tool-call-parser', '--chat-template', '--reasoning-parser', '--default-chat-template-kwargs', '--enable-prefix-caching', '--enable-chunked-prefill', '--enforce-eager']
      insertion_points:
        volumes: present    # overlay/sidecar mount anchor
        entrypoint: present  # sidecar invoke anchor
  vllm/long-vision:
    compose_path: models/qwen3.6-27b/vllm/compose/single/autoround-int4/long-vision.yml
    genesis_equipped: true
    genesis_equipped_evidence: compose contains GENESIS_* / _genesis token
    compose_service_template:
      source: models/qwen3.6-27b/vllm/compose/single/autoround-int4/long-vision.yml  # whole service definition captured verbatim from this file
      param_slots:
        ports: { source: E.default_port, value: 8020 }
        tensor_parallel_size: { token: '${TP}', source: E.tp, value: 1 }
        max_model_len: { token: '${MAX_MODEL_LEN}', source: E.max_ctx, value: 145000 }
        gpu_memory_utilization: { token: '${GPU_MEMORY_UTILIZATION}', source: E.mem_util, value: 0.95 }
        kv_cache_dtype: { token: '${KV_CACHE_DTYPE}', source: 'kv_arg(E.kv_format)', kv_format: turboquant_3bit_nc, value: 'turboquant_3bit_nc' }
        max_num_seqs: { token: '--max-num-seqs', source: E.max_num_seqs, value: 1 }
        speculative_config: { token: '--speculative-config', source: 'drafter[qwen-mtp-builtin].speculative_config_template' }
      governed_slots:
        trust_remote_code:
          token: '--trust-remote-code'
          present_in_shipped_compose: true
          policy: governed   # locked design v6 §88 security model
          emit_rule: 'only if arch trc gate resolves evidence-cited false-permitted; never blind-passthrough'
      constants:
        image: '${VLLM_IMAGE:-vllm/vllm-openai:nightly-${VLLM_NIGHTLY_SHA}}'   # captured constant; engine pin flows via env, NOT rewritten
        verbatim_from_compose: [shm_size, ipc, deploy.resources, model_cache_volume, base_environment, base_entrypoint, '--model', '--served-model-name', '--quantization', '--dtype', '--tool-call-parser', '--chat-template', '--reasoning-parser', '--default-chat-template-kwargs', '--enable-prefix-caching', '--enable-chunked-prefill', '--enforce-eager']
      insertion_points:
        volumes: present    # overlay/sidecar mount anchor
        entrypoint: present  # sidecar invoke anchor
  vllm/bounded-thinking:
    compose_path: models/qwen3.6-27b/vllm/compose/single/autoround-int4/bounded-thinking.yml
    genesis_equipped: true
    genesis_equipped_evidence: compose contains GENESIS_* / _genesis token
    compose_service_template:
      source: models/qwen3.6-27b/vllm/compose/single/autoround-int4/bounded-thinking.yml  # whole service definition captured verbatim from this file
      param_slots:
        ports: { source: E.default_port, value: 8020 }
        tensor_parallel_size: { token: '${TP}', source: E.tp, value: 1 }
        max_model_len: { token: '${MAX_MODEL_LEN}', source: E.max_ctx, value: 180000 }
        gpu_memory_utilization: { token: '${GPU_MEMORY_UTILIZATION}', source: E.mem_util, value: 0.95 }
        kv_cache_dtype: { token: '${KV_CACHE_DTYPE}', source: 'kv_arg(E.kv_format)', kv_format: turboquant_3bit_nc, value: 'turboquant_3bit_nc' }
        max_num_seqs: { token: '--max-num-seqs', source: E.max_num_seqs, value: 1 }
        speculative_config: { token: '--speculative-config', source: 'drafter[qwen-mtp-builtin].speculative_config_template' }
      governed_slots:
        trust_remote_code:
          token: '--trust-remote-code'
          present_in_shipped_compose: true
          policy: governed   # locked design v6 §88 security model
          emit_rule: 'only if arch trc gate resolves evidence-cited false-permitted; never blind-passthrough'
      constants:
        image: '${VLLM_IMAGE:-vllm/vllm-openai:nightly-${VLLM_NIGHTLY_SHA}}'   # captured constant; engine pin flows via env, NOT rewritten
        verbatim_from_compose: [shm_size, ipc, deploy.resources, model_cache_volume, base_environment, base_entrypoint, '--model', '--served-model-name', '--quantization', '--dtype', '--tool-call-parser', '--chat-template', '--reasoning-parser', '--default-chat-template-kwargs', '--enable-prefix-caching', '--enable-chunked-prefill', '--enforce-eager']
      insertion_points:
        volumes: present    # overlay/sidecar mount anchor
        entrypoint: present  # sidecar invoke anchor
  vllm/tools-text:
    compose_path: models/qwen3.6-27b/vllm/compose/single/autoround-int4/tools-text.yml
    genesis_equipped: true
    genesis_equipped_evidence: compose contains GENESIS_* / _genesis token
    compose_service_template:
      source: models/qwen3.6-27b/vllm/compose/single/autoround-int4/tools-text.yml  # whole service definition captured verbatim from this file
      param_slots:
        ports: { source: E.default_port, value: 8020 }
        tensor_parallel_size: { token: '${TP}', source: E.tp, value: 1 }
        max_model_len: { token: '${MAX_MODEL_LEN}', source: E.max_ctx, value: 75000 }
        gpu_memory_utilization: { token: '${GPU_MEMORY_UTILIZATION}', source: E.mem_util, value: 0.97 }
        kv_cache_dtype: { token: '${KV_CACHE_DTYPE}', source: 'kv_arg(E.kv_format)', kv_format: fp8_e5m2, value: 'fp8_e5m2' }
        max_num_seqs: { token: '--max-num-seqs', source: E.max_num_seqs, value: 1 }
        speculative_config: { token: '--speculative-config', source: 'drafter[qwen-mtp-builtin].speculative_config_template' }
      governed_slots:
        trust_remote_code:
          token: '--trust-remote-code'
          present_in_shipped_compose: true
          policy: governed   # locked design v6 §88 security model
          emit_rule: 'only if arch trc gate resolves evidence-cited false-permitted; never blind-passthrough'
      constants:
        image: '${VLLM_IMAGE:-vllm/vllm-openai:nightly-${VLLM_NIGHTLY_SHA}}'   # captured constant; engine pin flows via env, NOT rewritten
        verbatim_from_compose: [shm_size, ipc, deploy.resources, model_cache_volume, base_environment, base_entrypoint, '--model', '--served-model-name', '--quantization', '--dtype', '--tool-call-parser', '--chat-template', '--reasoning-parser', '--default-chat-template-kwargs', '--enable-prefix-caching', '--enable-chunked-prefill', '--enforce-eager']
      insertion_points:
        volumes: present    # overlay/sidecar mount anchor
        entrypoint: present  # sidecar invoke anchor
  vllm/minimal:
    compose_path: models/qwen3.6-27b/vllm/compose/single/autoround-int4/minimal.yml
    genesis_equipped: false
    genesis_equipped_evidence: no GENESIS_* token in compose and kv_format is not turboquant*
    compose_service_template:
      source: models/qwen3.6-27b/vllm/compose/single/autoround-int4/minimal.yml  # whole service definition captured verbatim from this file
      param_slots:
        ports: { source: E.default_port, value: 8020 }
        tensor_parallel_size: { token: '${TP}', source: E.tp, value: 1 }
        max_model_len: { token: '${MAX_MODEL_LEN}', source: E.max_ctx, value: 32768 }
        gpu_memory_utilization: { token: '${GPU_MEMORY_UTILIZATION}', source: E.mem_util, value: 0.92 }
        kv_cache_dtype: { token: '${KV_CACHE_DTYPE}', source: 'kv_arg(E.kv_format)', kv_format: fp8_e5m2, value: 'fp8_e5m2' }
        max_num_seqs: { token: '--max-num-seqs', source: E.max_num_seqs, value: 1 }
        speculative_config: omitted  # E.drafter is None -> --speculative-config not emitted
      governed_slots:
        trust_remote_code:
          token: '--trust-remote-code'
          present_in_shipped_compose: true
          policy: governed   # locked design v6 §88 security model
          emit_rule: 'only if arch trc gate resolves evidence-cited false-permitted; never blind-passthrough'
      constants:
        image: '${VLLM_IMAGE:-vllm/vllm-openai:nightly-${VLLM_NIGHTLY_SHA}}'   # captured constant; engine pin flows via env, NOT rewritten
        verbatim_from_compose: [shm_size, ipc, deploy.resources, model_cache_volume, base_environment, base_entrypoint, '--model', '--served-model-name', '--quantization', '--dtype', '--tool-call-parser', '--chat-template', '--reasoning-parser', '--default-chat-template-kwargs', '--enable-prefix-caching', '--enable-chunked-prefill', '--enforce-eager']
      insertion_points:
        volumes: present    # overlay/sidecar mount anchor
        entrypoint: present  # sidecar invoke anchor
  vllm/dual:
    compose_path: models/qwen3.6-27b/vllm/compose/dual/autoround-int4/fp8-mtp.yml
    genesis_equipped: false
    genesis_equipped_evidence: no GENESIS_* token in compose and kv_format is not turboquant*
    compose_service_template:
      source: models/qwen3.6-27b/vllm/compose/dual/autoround-int4/fp8-mtp.yml  # whole service definition captured verbatim from this file
      param_slots:
        ports: { source: E.default_port, value: 8010 }
        tensor_parallel_size: { token: '${TP}', source: E.tp, value: 2 }
        max_model_len: { token: '${MAX_MODEL_LEN}', source: E.max_ctx, value: 262144 }
        gpu_memory_utilization: { token: '${GPU_MEMORY_UTILIZATION}', source: E.mem_util, value: 0.92 }
        kv_cache_dtype: { token: '${KV_CACHE_DTYPE}', source: 'kv_arg(E.kv_format)', kv_format: fp8_e5m2, value: 'fp8_e5m2' }
        max_num_seqs: { token: '--max-num-seqs', source: E.max_num_seqs, value: 2 }
        speculative_config: { token: '--speculative-config', source: 'drafter[qwen-mtp-builtin].speculative_config_template' }
        nvlink_env: { source: E.requires_nvlink, value: false }
      governed_slots:
        trust_remote_code:
          token: '--trust-remote-code'
          present_in_shipped_compose: true
          policy: governed   # locked design v6 §88 security model
          emit_rule: 'only if arch trc gate resolves evidence-cited false-permitted; never blind-passthrough'
      constants:
        image: '${VLLM_IMAGE:-vllm/vllm-openai:nightly-${VLLM_NIGHTLY_SHA}}'   # captured constant; engine pin flows via env, NOT rewritten
        verbatim_from_compose: [shm_size, ipc, deploy.resources, model_cache_volume, base_environment, base_entrypoint, '--model', '--served-model-name', '--quantization', '--dtype', '--tool-call-parser', '--chat-template', '--reasoning-parser', '--default-chat-template-kwargs', '--enable-prefix-caching', '--enable-chunked-prefill', '--enforce-eager']
      insertion_points:
        volumes: present    # overlay/sidecar mount anchor
        entrypoint: present  # sidecar invoke anchor
  vllm/dual-turbo:
    compose_path: models/qwen3.6-27b/vllm/compose/dual/autoround-int4/turbo.yml
    genesis_equipped: true
    genesis_equipped_evidence: compose contains GENESIS_* / _genesis token
    compose_service_template:
      source: models/qwen3.6-27b/vllm/compose/dual/autoround-int4/turbo.yml  # whole service definition captured verbatim from this file
      param_slots:
        ports: { source: E.default_port, value: 8011 }
        tensor_parallel_size: { token: '${TP}', source: E.tp, value: 2 }
        max_model_len: { token: '${MAX_MODEL_LEN}', source: E.max_ctx, value: 262144 }
        gpu_memory_utilization: { token: '${GPU_MEMORY_UTILIZATION}', source: E.mem_util, value: 0.85 }
        kv_cache_dtype: { token: '${KV_CACHE_DTYPE}', source: 'kv_arg(E.kv_format)', kv_format: turboquant_3bit_nc, value: 'turboquant_3bit_nc' }
        max_num_seqs: { token: '--max-num-seqs', source: E.max_num_seqs, value: 4 }
        speculative_config: { token: '--speculative-config', source: 'drafter[qwen-mtp-builtin].speculative_config_template' }
        nvlink_env: { source: E.requires_nvlink, value: false }
      governed_slots:
        trust_remote_code:
          token: '--trust-remote-code'
          present_in_shipped_compose: true
          policy: governed   # locked design v6 §88 security model
          emit_rule: 'only if arch trc gate resolves evidence-cited false-permitted; never blind-passthrough'
      constants:
        image: '${VLLM_IMAGE:-vllm/vllm-openai:nightly-${VLLM_NIGHTLY_SHA}}'   # captured constant; engine pin flows via env, NOT rewritten
        verbatim_from_compose: [shm_size, ipc, deploy.resources, model_cache_volume, base_environment, base_entrypoint, '--model', '--served-model-name', '--quantization', '--dtype', '--tool-call-parser', '--chat-template', '--reasoning-parser', '--default-chat-template-kwargs', '--enable-prefix-caching', '--enable-chunked-prefill', '--enforce-eager']
      insertion_points:
        volumes: present    # overlay/sidecar mount anchor
        entrypoint: present  # sidecar invoke anchor
  vllm/dual-dflash:
    compose_path: models/qwen3.6-27b/vllm/compose/dual/autoround-int4/dflash.yml
    genesis_equipped: false
    genesis_equipped_evidence: no GENESIS_* token in compose and kv_format is not turboquant*
    compose_service_template:
      source: models/qwen3.6-27b/vllm/compose/dual/autoround-int4/dflash.yml  # whole service definition captured verbatim from this file
      param_slots:
        ports: { source: E.default_port, value: 8012 }
        tensor_parallel_size: { token: '${TP}', source: E.tp, value: 2 }
        max_model_len: { token: '${MAX_MODEL_LEN}', source: E.max_ctx, value: 185000 }
        gpu_memory_utilization: { token: '${GPU_MEMORY_UTILIZATION}', source: E.mem_util, value: 0.95 }
        kv_cache_dtype: { token: '${KV_CACHE_DTYPE}', source: 'kv_arg(E.kv_format)', kv_format: fp16, value: null }
        max_num_seqs: { token: '--max-num-seqs', source: E.max_num_seqs, value: 1 }
        speculative_config: { token: '--speculative-config', source: 'drafter[zlab-qwen-dflash].speculative_config_template' }
        nvlink_env: { source: E.requires_nvlink, value: false }
      governed_slots:
        trust_remote_code:
          token: '--trust-remote-code'
          present_in_shipped_compose: true
          policy: governed   # locked design v6 §88 security model
          emit_rule: 'only if arch trc gate resolves evidence-cited false-permitted; never blind-passthrough'
      constants:
        image: '${VLLM_IMAGE:-vllm/vllm-openai:nightly-${VLLM_NIGHTLY_SHA}}'   # captured constant; engine pin flows via env, NOT rewritten
        verbatim_from_compose: [shm_size, ipc, deploy.resources, model_cache_volume, base_environment, base_entrypoint, '--model', '--served-model-name', '--quantization', '--dtype', '--tool-call-parser', '--chat-template', '--reasoning-parser', '--default-chat-template-kwargs', '--enable-prefix-caching', '--enable-chunked-prefill', '--enforce-eager']
      insertion_points:
        volumes: present    # overlay/sidecar mount anchor
        entrypoint: present  # sidecar invoke anchor
  vllm/dual-dflash-noviz:
    compose_path: models/qwen3.6-27b/vllm/compose/dual/autoround-int4/dflash-noviz.yml
    genesis_equipped: false
    genesis_equipped_evidence: no GENESIS_* token in compose and kv_format is not turboquant*
    compose_service_template:
      source: models/qwen3.6-27b/vllm/compose/dual/autoround-int4/dflash-noviz.yml  # whole service definition captured verbatim from this file
      param_slots:
        ports: { source: E.default_port, value: 8013 }
        tensor_parallel_size: { token: '${TP}', source: E.tp, value: 2 }
        max_model_len: { token: '${MAX_MODEL_LEN}', source: E.max_ctx, value: 200000 }
        gpu_memory_utilization: { token: '${GPU_MEMORY_UTILIZATION}', source: E.mem_util, value: 0.95 }
        kv_cache_dtype: { token: '${KV_CACHE_DTYPE}', source: 'kv_arg(E.kv_format)', kv_format: fp16, value: null }
        max_num_seqs: { token: '--max-num-seqs', source: E.max_num_seqs, value: 1 }
        speculative_config: { token: '--speculative-config', source: 'drafter[zlab-qwen-dflash].speculative_config_template' }
        nvlink_env: { source: E.requires_nvlink, value: false }
      governed_slots:
        trust_remote_code:
          token: '--trust-remote-code'
          present_in_shipped_compose: true
          policy: governed   # locked design v6 §88 security model
          emit_rule: 'only if arch trc gate resolves evidence-cited false-permitted; never blind-passthrough'
      constants:
        image: '${VLLM_IMAGE:-vllm/vllm-openai:nightly-${VLLM_NIGHTLY_SHA}}'   # captured constant; engine pin flows via env, NOT rewritten
        verbatim_from_compose: [shm_size, ipc, deploy.resources, model_cache_volume, base_environment, base_entrypoint, '--model', '--served-model-name', '--quantization', '--dtype', '--tool-call-parser', '--chat-template', '--reasoning-parser', '--default-chat-template-kwargs', '--enable-prefix-caching', '--enable-chunked-prefill', '--enforce-eager']
      insertion_points:
        volumes: present    # overlay/sidecar mount anchor
        entrypoint: present  # sidecar invoke anchor
  vllm/dual-bf16:
    compose_path: models/qwen3.6-27b/vllm/compose/dual/autoround-int4/bf16.yml
    genesis_equipped: false
    genesis_equipped_evidence: no GENESIS_* token in compose and kv_format is not turboquant*
    compose_service_template:
      source: models/qwen3.6-27b/vllm/compose/dual/autoround-int4/bf16.yml  # whole service definition captured verbatim from this file
      param_slots:
        ports: { source: E.default_port, value: 8012 }
        tensor_parallel_size: { token: '${TP}', source: E.tp, value: 2 }
        max_model_len: { token: '${MAX_MODEL_LEN}', source: E.max_ctx, value: 200000 }
        gpu_memory_utilization: { token: '${GPU_MEMORY_UTILIZATION}', source: E.mem_util, value: 0.92 }
        kv_cache_dtype: { token: '${KV_CACHE_DTYPE}', source: 'kv_arg(E.kv_format)', kv_format: bf16, value: null }
        max_num_seqs: { token: '--max-num-seqs', source: E.max_num_seqs, value: 1 }
        speculative_config: { token: '--speculative-config', source: 'drafter[qwen-mtp-builtin].speculative_config_template' }
      governed_slots:
        trust_remote_code:
          token: '--trust-remote-code'
          present_in_shipped_compose: true
          policy: governed   # locked design v6 §88 security model
          emit_rule: 'only if arch trc gate resolves evidence-cited false-permitted; never blind-passthrough'
      constants:
        image: '${VLLM_IMAGE:-vllm/vllm-openai:nightly-${VLLM_NIGHTLY_SHA}}'   # captured constant; engine pin flows via env, NOT rewritten
        verbatim_from_compose: [shm_size, ipc, deploy.resources, model_cache_volume, base_environment, base_entrypoint, '--model', '--served-model-name', '--quantization', '--dtype', '--tool-call-parser', '--chat-template', '--reasoning-parser', '--default-chat-template-kwargs', '--enable-prefix-caching', '--enable-chunked-prefill', '--enforce-eager']
      insertion_points:
        volumes: present    # overlay/sidecar mount anchor
        entrypoint: present  # sidecar invoke anchor
  vllm/dual-int8:
    compose_path: models/qwen3.6-27b/vllm/compose/dual/autoround-int4/int8.yml
    genesis_equipped: false
    genesis_equipped_evidence: no GENESIS_* token in compose and kv_format is not turboquant*
    compose_service_template:
      source: models/qwen3.6-27b/vllm/compose/dual/autoround-int4/int8.yml  # whole service definition captured verbatim from this file
      param_slots:
        ports: { source: E.default_port, value: 8011 }
        tensor_parallel_size: { token: '${TP}', source: E.tp, value: 2 }
        max_model_len: { token: '${MAX_MODEL_LEN}', source: E.max_ctx, value: 262144 }
        gpu_memory_utilization: { token: '${GPU_MEMORY_UTILIZATION}', source: E.mem_util, value: 0.92 }
        kv_cache_dtype: { token: '${KV_CACHE_DTYPE}', source: 'kv_arg(E.kv_format)', kv_format: int8_per_token_head, value: 'auto+PTH' }
        max_num_seqs: { token: '--max-num-seqs', source: E.max_num_seqs, value: 2 }
        speculative_config: { token: '--speculative-config', source: 'drafter[qwen-mtp-builtin].speculative_config_template' }
      governed_slots:
        trust_remote_code:
          token: '--trust-remote-code'
          present_in_shipped_compose: true
          policy: governed   # locked design v6 §88 security model
          emit_rule: 'only if arch trc gate resolves evidence-cited false-permitted; never blind-passthrough'
      constants:
        image: '${VLLM_IMAGE:-vllm/vllm-openai:nightly-${VLLM_NIGHTLY_SHA}}'   # captured constant; engine pin flows via env, NOT rewritten
        verbatim_from_compose: [shm_size, ipc, deploy.resources, model_cache_volume, base_environment, base_entrypoint, '--model', '--served-model-name', '--quantization', '--dtype', '--tool-call-parser', '--chat-template', '--reasoning-parser', '--default-chat-template-kwargs', '--enable-prefix-caching', '--enable-chunked-prefill', '--enforce-eager']
      insertion_points:
        volumes: present    # overlay/sidecar mount anchor
        entrypoint: present  # sidecar invoke anchor
  vllm/dual-tq3-mtp:
    compose_path: models/qwen3.6-27b/vllm/compose/dual/autoround-int4/tq3-mtp.yml
    genesis_equipped: true
    genesis_equipped_evidence: kv_format 'turboquant_3bit_nc' starts with 'turboquant'
    compose_service_template:
      source: models/qwen3.6-27b/vllm/compose/dual/autoround-int4/tq3-mtp.yml  # whole service definition captured verbatim from this file
      param_slots:
        ports: { source: E.default_port, value: 8013 }
        tensor_parallel_size: { token: '${TP}', source: E.tp, value: 2 }
        max_model_len: { token: '${MAX_MODEL_LEN}', source: E.max_ctx, value: 262144 }
        gpu_memory_utilization: { token: '${GPU_MEMORY_UTILIZATION}', source: E.mem_util, value: 0.92 }
        kv_cache_dtype: { token: '${KV_CACHE_DTYPE}', source: 'kv_arg(E.kv_format)', kv_format: turboquant_3bit_nc, value: 'turboquant_3bit_nc' }
        max_num_seqs: { token: '--max-num-seqs', source: E.max_num_seqs, value: 2 }
        speculative_config: { token: '--speculative-config', source: 'drafter[qwen-mtp-builtin].speculative_config_template' }
      governed_slots:
        trust_remote_code:
          token: '--trust-remote-code'
          present_in_shipped_compose: true
          policy: governed   # locked design v6 §88 security model
          emit_rule: 'only if arch trc gate resolves evidence-cited false-permitted; never blind-passthrough'
      constants:
        image: '${VLLM_IMAGE:-vllm/vllm-openai:nightly-${VLLM_NIGHTLY_SHA}}'   # captured constant; engine pin flows via env, NOT rewritten
        verbatim_from_compose: [shm_size, ipc, deploy.resources, model_cache_volume, base_environment, base_entrypoint, '--model', '--served-model-name', '--quantization', '--dtype', '--tool-call-parser', '--chat-template', '--reasoning-parser', '--default-chat-template-kwargs', '--enable-prefix-caching', '--enable-chunked-prefill', '--enforce-eager']
      insertion_points:
        volumes: present    # overlay/sidecar mount anchor
        entrypoint: present  # sidecar invoke anchor
  vllm/dual-tq3-mtp-genesis:
    compose_path: models/qwen3.6-27b/vllm/compose/dual/autoround-int4/tq3-mtp-genesis.yml
    genesis_equipped: true
    genesis_equipped_evidence: compose contains GENESIS_* / _genesis token
    compose_service_template:
      source: models/qwen3.6-27b/vllm/compose/dual/autoround-int4/tq3-mtp-genesis.yml  # whole service definition captured verbatim from this file
      param_slots:
        ports: { source: E.default_port, value: 8015 }
        tensor_parallel_size: { token: '${TP}', source: E.tp, value: 2 }
        max_model_len: { token: '${MAX_MODEL_LEN}', source: E.max_ctx, value: 262144 }
        gpu_memory_utilization: { token: '${GPU_MEMORY_UTILIZATION}', source: E.mem_util, value: 0.85 }
        kv_cache_dtype: { token: '${KV_CACHE_DTYPE}', source: 'kv_arg(E.kv_format)', kv_format: turboquant_3bit_nc, value: 'turboquant_3bit_nc' }
        max_num_seqs: { token: '--max-num-seqs', source: E.max_num_seqs, value: 2 }
        speculative_config: { token: '--speculative-config', source: 'drafter[qwen-mtp-builtin].speculative_config_template' }
      governed_slots:
        trust_remote_code:
          token: '--trust-remote-code'
          present_in_shipped_compose: true
          policy: governed   # locked design v6 §88 security model
          emit_rule: 'only if arch trc gate resolves evidence-cited false-permitted; never blind-passthrough'
      constants:
        image: '${VLLM_IMAGE:-vllm/vllm-openai:nightly-${VLLM_NIGHTLY_SHA}}'   # captured constant; engine pin flows via env, NOT rewritten
        verbatim_from_compose: [shm_size, ipc, deploy.resources, model_cache_volume, base_environment, base_entrypoint, '--model', '--served-model-name', '--quantization', '--dtype', '--tool-call-parser', '--chat-template', '--reasoning-parser', '--default-chat-template-kwargs', '--enable-prefix-caching', '--enable-chunked-prefill', '--enforce-eager']
      insertion_points:
        volumes: present    # overlay/sidecar mount anchor
        entrypoint: present  # sidecar invoke anchor
  vllm/dual-tq3-nomtp:
    compose_path: models/qwen3.6-27b/vllm/compose/dual/autoround-int4/tq3-nomtp.yml
    genesis_equipped: true
    genesis_equipped_evidence: kv_format 'turboquant_3bit_nc' starts with 'turboquant'
    compose_service_template:
      source: models/qwen3.6-27b/vllm/compose/dual/autoround-int4/tq3-nomtp.yml  # whole service definition captured verbatim from this file
      param_slots:
        ports: { source: E.default_port, value: 8014 }
        tensor_parallel_size: { token: '${TP}', source: E.tp, value: 2 }
        max_model_len: { token: '${MAX_MODEL_LEN}', source: E.max_ctx, value: 262144 }
        gpu_memory_utilization: { token: '${GPU_MEMORY_UTILIZATION}', source: E.mem_util, value: 0.92 }
        kv_cache_dtype: { token: '${KV_CACHE_DTYPE}', source: 'kv_arg(E.kv_format)', kv_format: turboquant_3bit_nc, value: 'turboquant_3bit_nc' }
        max_num_seqs: { token: '--max-num-seqs', source: E.max_num_seqs, value: 2 }
        speculative_config: omitted  # E.drafter is None -> --speculative-config not emitted
      governed_slots:
        trust_remote_code:
          token: '--trust-remote-code'
          present_in_shipped_compose: true
          policy: governed   # locked design v6 §88 security model
          emit_rule: 'only if arch trc gate resolves evidence-cited false-permitted; never blind-passthrough'
      constants:
        image: '${VLLM_IMAGE:-vllm/vllm-openai:nightly-${VLLM_NIGHTLY_SHA}}'   # captured constant; engine pin flows via env, NOT rewritten
        verbatim_from_compose: [shm_size, ipc, deploy.resources, model_cache_volume, base_environment, base_entrypoint, '--model', '--served-model-name', '--quantization', '--dtype', '--tool-call-parser', '--chat-template', '--reasoning-parser', '--default-chat-template-kwargs', '--enable-prefix-caching', '--enable-chunked-prefill', '--enforce-eager']
      insertion_points:
        volumes: present    # overlay/sidecar mount anchor
        entrypoint: present  # sidecar invoke anchor
  vllm/dual-carnice-bf16mtp:
    compose_path: models/qwen3.6-27b/vllm/compose/dual/carnice-bf16mtp/bf16-mtp.yml
    genesis_equipped: false
    genesis_equipped_evidence: no GENESIS_* token in compose and kv_format is not turboquant*
    compose_service_template:
      source: models/qwen3.6-27b/vllm/compose/dual/carnice-bf16mtp/bf16-mtp.yml  # whole service definition captured verbatim from this file
      param_slots:
        ports: { source: E.default_port, value: 8070 }
        tensor_parallel_size: { token: '${TP}', source: E.tp, value: 2 }
        max_model_len: { token: '${MAX_MODEL_LEN}', source: E.max_ctx, value: 262144 }
        gpu_memory_utilization: { token: '${GPU_MEMORY_UTILIZATION}', source: E.mem_util, value: 0.92 }
        kv_cache_dtype: { token: '${KV_CACHE_DTYPE}', source: 'kv_arg(E.kv_format)', kv_format: fp8_e5m2, value: 'fp8_e5m2' }
        max_num_seqs: { token: '--max-num-seqs', source: E.max_num_seqs, value: 2 }
        speculative_config: { token: '--speculative-config', source: 'drafter[qwen-mtp-builtin].speculative_config_template' }
      governed_slots:
        trust_remote_code:
          token: '--trust-remote-code'
          present_in_shipped_compose: true
          policy: governed   # locked design v6 §88 security model
          emit_rule: 'only if arch trc gate resolves evidence-cited false-permitted; never blind-passthrough'
      constants:
        image: '${VLLM_IMAGE:-vllm/vllm-openai:nightly-${VLLM_NIGHTLY_SHA}}'   # captured constant; engine pin flows via env, NOT rewritten
        verbatim_from_compose: [shm_size, ipc, deploy.resources, model_cache_volume, base_environment, base_entrypoint, '--model', '--served-model-name', '--quantization', '--dtype', '--tool-call-parser', '--chat-template', '--reasoning-parser', '--default-chat-template-kwargs', '--enable-prefix-caching', '--enable-chunked-prefill', '--enforce-eager']
      insertion_points:
        volumes: present    # overlay/sidecar mount anchor
        entrypoint: present  # sidecar invoke anchor
  vllm/dual-qwopus-bf16mtp:
    compose_path: models/qwen3.6-27b/vllm/compose/dual/qwopus-bf16mtp/bf16-mtp.yml
    genesis_equipped: false
    genesis_equipped_evidence: no GENESIS_* token in compose and kv_format is not turboquant*
    compose_service_template:
      source: models/qwen3.6-27b/vllm/compose/dual/qwopus-bf16mtp/bf16-mtp.yml  # whole service definition captured verbatim from this file
      param_slots:
        ports: { source: E.default_port, value: 8071 }
        tensor_parallel_size: { token: '${TP}', source: E.tp, value: 2 }
        max_model_len: { token: '${MAX_MODEL_LEN}', source: E.max_ctx, value: 262144 }
        gpu_memory_utilization: { token: '${GPU_MEMORY_UTILIZATION}', source: E.mem_util, value: 0.92 }
        kv_cache_dtype: { token: '${KV_CACHE_DTYPE}', source: 'kv_arg(E.kv_format)', kv_format: fp8_e5m2, value: 'fp8_e5m2' }
        max_num_seqs: { token: '--max-num-seqs', source: E.max_num_seqs, value: 2 }
        speculative_config: { token: '--speculative-config', source: 'drafter[qwen-mtp-builtin].speculative_config_template' }
      governed_slots:
        trust_remote_code:
          token: '--trust-remote-code'
          present_in_shipped_compose: true
          policy: governed   # locked design v6 §88 security model
          emit_rule: 'only if arch trc gate resolves evidence-cited false-permitted; never blind-passthrough'
      constants:
        image: '${VLLM_IMAGE:-vllm/vllm-openai:nightly-${VLLM_NIGHTLY_SHA}}'   # captured constant; engine pin flows via env, NOT rewritten
        verbatim_from_compose: [shm_size, ipc, deploy.resources, model_cache_volume, base_environment, base_entrypoint, '--model', '--served-model-name', '--quantization', '--dtype', '--tool-call-parser', '--chat-template', '--reasoning-parser', '--default-chat-template-kwargs', '--enable-prefix-caching', '--enable-chunked-prefill', '--enforce-eager']
      insertion_points:
        volumes: present    # overlay/sidecar mount anchor
        entrypoint: present  # sidecar invoke anchor
  vllm/dual4:
    compose_path: models/qwen3.6-27b/vllm/compose/multi4/autoround-int4/fp8-mtp.yml
    genesis_equipped: false
    genesis_equipped_evidence: no GENESIS_* token in compose and kv_format is not turboquant*
    compose_service_template:
      source: models/qwen3.6-27b/vllm/compose/multi4/autoround-int4/fp8-mtp.yml  # whole service definition captured verbatim from this file
      param_slots:
        ports: { source: E.default_port, value: 8015 }
        tensor_parallel_size: { token: '${TP}', source: E.tp, value: 4 }
        max_model_len: { token: '${MAX_MODEL_LEN}', source: E.max_ctx, value: 262144 }
        gpu_memory_utilization: { token: '${GPU_MEMORY_UTILIZATION}', source: E.mem_util, value: 0.92 }
        kv_cache_dtype: { token: '${KV_CACHE_DTYPE}', source: 'kv_arg(E.kv_format)', kv_format: fp8_e5m2, value: 'fp8_e5m2' }
        max_num_seqs: { token: '--max-num-seqs', source: E.max_num_seqs, value: 4 }
        speculative_config: { token: '--speculative-config', source: 'drafter[qwen-mtp-builtin].speculative_config_template' }
      governed_slots:
        trust_remote_code:
          token: '--trust-remote-code'
          present_in_shipped_compose: true
          policy: governed   # locked design v6 §88 security model
          emit_rule: 'only if arch trc gate resolves evidence-cited false-permitted; never blind-passthrough'
      constants:
        image: '${VLLM_IMAGE:-vllm/vllm-openai:nightly-${VLLM_NIGHTLY_SHA}}'   # captured constant; engine pin flows via env, NOT rewritten
        verbatim_from_compose: [shm_size, ipc, deploy.resources, model_cache_volume, base_environment, base_entrypoint, '--model', '--served-model-name', '--quantization', '--dtype', '--tool-call-parser', '--chat-template', '--reasoning-parser', '--default-chat-template-kwargs', '--enable-prefix-caching', '--enable-chunked-prefill', '--enforce-eager']
      insertion_points:
        volumes: present    # overlay/sidecar mount anchor
        entrypoint: present  # sidecar invoke anchor
  vllm/dual4-dflash:
    compose_path: models/qwen3.6-27b/vllm/compose/multi4/autoround-int4/dflash.yml
    genesis_equipped: false
    genesis_equipped_evidence: no GENESIS_* token in compose and kv_format is not turboquant*
    compose_service_template:
      source: models/qwen3.6-27b/vllm/compose/multi4/autoround-int4/dflash.yml  # whole service definition captured verbatim from this file
      param_slots:
        ports: { source: E.default_port, value: 8016 }
        tensor_parallel_size: { token: '${TP}', source: E.tp, value: 4 }
        max_model_len: { token: '${MAX_MODEL_LEN}', source: E.max_ctx, value: 262144 }
        gpu_memory_utilization: { token: '${GPU_MEMORY_UTILIZATION}', source: E.mem_util, value: 0.95 }
        kv_cache_dtype: { token: '${KV_CACHE_DTYPE}', source: 'kv_arg(E.kv_format)', kv_format: fp16, value: null }
        max_num_seqs: { token: '--max-num-seqs', source: E.max_num_seqs, value: 2 }
        speculative_config: { token: '--speculative-config', source: 'drafter[zlab-qwen-dflash].speculative_config_template' }
      governed_slots:
        trust_remote_code:
          token: '--trust-remote-code'
          present_in_shipped_compose: true
          policy: governed   # locked design v6 §88 security model
          emit_rule: 'only if arch trc gate resolves evidence-cited false-permitted; never blind-passthrough'
      constants:
        image: '${VLLM_IMAGE:-vllm/vllm-openai:nightly-${VLLM_NIGHTLY_SHA}}'   # captured constant; engine pin flows via env, NOT rewritten
        verbatim_from_compose: [shm_size, ipc, deploy.resources, model_cache_volume, base_environment, base_entrypoint, '--model', '--served-model-name', '--quantization', '--dtype', '--tool-call-parser', '--chat-template', '--reasoning-parser', '--default-chat-template-kwargs', '--enable-prefix-caching', '--enable-chunked-prefill', '--enforce-eager']
      insertion_points:
        volumes: present    # overlay/sidecar mount anchor
        entrypoint: present  # sidecar invoke anchor
  vllm/gemma-mtp-tp1:
    compose_path: models/gemma-4-31b/vllm/compose/single/autoround-int4/fp8-mtp.yml
    genesis_equipped: false
    genesis_equipped_evidence: no GENESIS_* token in compose and kv_format is not turboquant*
    compose_service_template:
      source: models/gemma-4-31b/vllm/compose/single/autoround-int4/fp8-mtp.yml  # whole service definition captured verbatim from this file
      param_slots:
        ports: { source: E.default_port, value: 8031 }
        tensor_parallel_size: { token: '${TP}', source: E.tp, value: 1 }
        max_model_len: { token: '${MAX_MODEL_LEN}', source: E.max_ctx, value: 8192 }
        gpu_memory_utilization: { token: '${GPU_MEMORY_UTILIZATION}', source: E.mem_util, value: 0.95 }
        kv_cache_dtype: { token: '${KV_CACHE_DTYPE}', source: 'kv_arg(E.kv_format)', kv_format: fp8_e4m3, value: 'fp8' }
        max_num_seqs: { token: '--max-num-seqs', source: E.max_num_seqs, value: 256 }
        speculative_config: { token: '--speculative-config', source: 'drafter[gemma-it-assistant].speculative_config_template' }
      governed_slots:
        trust_remote_code:
          token: '--trust-remote-code'
          present_in_shipped_compose: true
          policy: governed   # locked design v6 §88 security model
          emit_rule: 'only if arch trc gate resolves evidence-cited false-permitted; never blind-passthrough'
      constants:
        image: '${VLLM_IMAGE:-vllm/vllm-openai:v0.21.0}'   # captured constant; Gemma 31B vLLM survivors pin immutable v0.21.0
        verbatim_from_compose: [shm_size, ipc, deploy.resources, model_cache_volume, base_environment, base_entrypoint, '--model', '--served-model-name', '--quantization', '--dtype', '--tool-call-parser', '--chat-template', '--reasoning-parser', '--default-chat-template-kwargs', '--enable-prefix-caching', '--enable-chunked-prefill', '--enforce-eager']
      insertion_points:
        volumes: present    # overlay/sidecar mount anchor
        entrypoint: absent  # sidecar invoke anchor
  vllm/gemma-bf16-mtp:
    compose_path: models/gemma-4-31b/vllm/compose/dual/autoround-int4/bf16-mtp.yml
    genesis_equipped: false
    genesis_equipped_evidence: no GENESIS_* token in compose and kv_format is not turboquant*
    compose_service_template:
      source: models/gemma-4-31b/vllm/compose/dual/autoround-int4/bf16-mtp.yml  # whole service definition captured verbatim from this file
      param_slots:
        ports: { source: E.default_port, value: 8030 }
        tensor_parallel_size: { token: '${TP}', source: E.tp, value: 2 }
        max_model_len: { token: '${MAX_MODEL_LEN}', source: E.max_ctx, value: 32768 }
        gpu_memory_utilization: { token: '${GPU_MEMORY_UTILIZATION}', source: E.mem_util, value: 0.92 }
        kv_cache_dtype: { token: '${KV_CACHE_DTYPE}', source: 'kv_arg(E.kv_format)', kv_format: bf16, value: null }
        max_num_seqs: { token: '--max-num-seqs', source: E.max_num_seqs, value: 4 }
        speculative_config: { token: '--speculative-config', source: 'drafter[gemma-it-assistant].speculative_config_template' }
        nvlink_env: { source: E.requires_nvlink, value: false }
      governed_slots:
        trust_remote_code:
          token: '--trust-remote-code'
          present_in_shipped_compose: true
          policy: governed   # locked design v6 §88 security model
          emit_rule: 'only if arch trc gate resolves evidence-cited false-permitted; never blind-passthrough'
      constants:
        image: '${VLLM_IMAGE:-vllm/vllm-openai:v0.21.0}'   # captured constant; Gemma 31B vLLM survivors pin immutable v0.21.0
        verbatim_from_compose: [shm_size, ipc, deploy.resources, model_cache_volume, base_environment, base_entrypoint, '--model', '--served-model-name', '--quantization', '--dtype', '--tool-call-parser', '--chat-template', '--reasoning-parser', '--default-chat-template-kwargs', '--enable-prefix-caching', '--enable-chunked-prefill', '--enforce-eager']
      insertion_points:
        volumes: present    # overlay/sidecar mount anchor
        entrypoint: present  # sidecar invoke anchor
  vllm/gemma-int8-mtp:
    compose_path: models/gemma-4-31b/vllm/compose/dual/autoround-int4/int8.yml
    genesis_equipped: false
    genesis_equipped_evidence: no GENESIS_* token in compose and kv_format is not turboquant*
    compose_service_template:
      source: models/gemma-4-31b/vllm/compose/dual/autoround-int4/int8.yml  # whole service definition captured verbatim from this file
      param_slots:
        ports: { source: E.default_port, value: 8032 }
        tensor_parallel_size: { token: '${TP}', source: E.tp, value: 2 }
        max_model_len: { token: '${MAX_MODEL_LEN:-${CTX}}', source: E.max_ctx, value: 98304 }
        gpu_memory_utilization: { token: '${GPU_MEMORY_UTILIZATION}', source: E.mem_util, value: 0.95 }
        kv_cache_dtype: { token: '${KV_CACHE_DTYPE}', source: 'kv_arg(E.kv_format)', kv_format: int8_per_token_head, value: 'auto+PTH' }
        max_num_seqs: { token: '--max-num-seqs', source: E.max_num_seqs, value: 4 }
        speculative_config: { token: '--speculative-config', source: 'drafter[gemma-it-assistant].speculative_config_template' }
        nvlink_env: { source: E.requires_nvlink, value: false }
      governed_slots:
        trust_remote_code:
          token: '--trust-remote-code'
          present_in_shipped_compose: true
          policy: governed   # locked design v6 §88 security model
          emit_rule: 'only if arch trc gate resolves evidence-cited false-permitted; never blind-passthrough'
      constants:
        image: '${VLLM_IMAGE:-vllm/vllm-openai:v0.21.0}'   # captured constant; Gemma 31B vLLM survivors pin immutable v0.21.0
        verbatim_from_compose: [shm_size, ipc, deploy.resources, model_cache_volume, base_environment, base_entrypoint, '--model', '--served-model-name', '--quantization', '--dtype', '--tool-call-parser', '--chat-template', '--reasoning-parser', '--default-chat-template-kwargs', '--enable-prefix-caching', '--enable-chunked-prefill', '--enforce-eager']
      insertion_points:
        volumes: present    # overlay/sidecar mount anchor
        entrypoint: present  # sidecar invoke anchor
  vllm/gemma-26ba4b-single:
    compose_path: models/gemma-4-26b-a4b/vllm/compose/single/awq/int8.yml
    genesis_equipped: false
    genesis_equipped_evidence: no GENESIS_* token in compose and kv_format is not turboquant*
    compose_service_template:
      source: models/gemma-4-26b-a4b/vllm/compose/single/awq/int8.yml  # whole service definition captured verbatim from this file
      param_slots:
        ports: { source: E.default_port, value: 8040 }
        tensor_parallel_size: { token: '${TP}', source: E.tp, value: 1 }
        max_model_len: { token: '${MAX_MODEL_LEN}', source: E.max_ctx, value: 176000 }
        gpu_memory_utilization: { token: '${GPU_MEMORY_UTILIZATION}', source: E.mem_util, value: 0.94 }
        kv_cache_dtype: { token: '${KV_CACHE_DTYPE}', source: 'kv_arg(E.kv_format)', kv_format: int8_per_token_head, value: 'auto+PTH' }
        max_num_seqs: { token: '--max-num-seqs', source: E.max_num_seqs, value: 256 }
        speculative_config: { token: '--speculative-config', source: 'drafter[gemma-26b-it-assistant].speculative_config_template' }
      governed_slots:
        trust_remote_code:
          token: '--trust-remote-code'
          present_in_shipped_compose: true
          policy: governed   # locked design v6 §88 security model
          emit_rule: 'only if arch trc gate resolves evidence-cited false-permitted; never blind-passthrough'
      constants:
        image: '${VLLM_IMAGE:-vllm/vllm-openai:v0.22.0}'   # captured constant; engine pin flows via env, NOT rewritten
        verbatim_from_compose: [shm_size, ipc, deploy.resources, model_cache_volume, base_environment, base_entrypoint, '--model', '--served-model-name', '--quantization', '--dtype', '--tool-call-parser', '--chat-template', '--reasoning-parser', '--default-chat-template-kwargs', '--enable-prefix-caching', '--enable-chunked-prefill', '--enforce-eager']
      insertion_points:
        volumes: present    # overlay/sidecar mount anchor (PR #40391 mount)
        entrypoint: present  # sidecar invoke anchor (PR #40391 install.sh entrypoint)
  vllm/gemma-26ba4b-dual:
    compose_path: models/gemma-4-26b-a4b/vllm/compose/dual/awq/mtp.yml
    genesis_equipped: false
    genesis_equipped_evidence: no GENESIS_* token in compose and kv_format is not turboquant*
    compose_service_template:
      source: models/gemma-4-26b-a4b/vllm/compose/dual/awq/mtp.yml  # whole service definition captured verbatim from this file
      param_slots:
        ports: { source: E.default_port, value: 8041 }
        tensor_parallel_size: { token: '${TP}', source: E.tp, value: 2 }
        max_model_len: { token: '${MAX_MODEL_LEN}', source: E.max_ctx, value: 262144 }
        gpu_memory_utilization: { token: '${GPU_MEMORY_UTILIZATION}', source: E.mem_util, value: 0.92 }
        kv_cache_dtype: { token: '${KV_CACHE_DTYPE}', source: 'kv_arg(E.kv_format)', kv_format: bf16, value: null }
        max_num_seqs: { token: '--max-num-seqs', source: E.max_num_seqs, value: 256 }
        speculative_config: { token: '--speculative-config', source: 'drafter[gemma-26b-it-assistant].speculative_config_template' }
      governed_slots:
        trust_remote_code:
          token: '--trust-remote-code'
          present_in_shipped_compose: true
          policy: governed   # locked design v6 §88 security model
          emit_rule: 'only if arch trc gate resolves evidence-cited false-permitted; never blind-passthrough'
      constants:
        image: '${VLLM_IMAGE:-vllm/vllm-openai:v0.22.0}'   # captured constant; engine pin flows via env, NOT rewritten
        verbatim_from_compose: [shm_size, ipc, deploy.resources, model_cache_volume, base_environment, base_entrypoint, '--model', '--served-model-name', '--quantization', '--dtype', '--tool-call-parser', '--chat-template', '--reasoning-parser', '--default-chat-template-kwargs', '--enable-prefix-caching', '--enable-chunked-prefill', '--enforce-eager']
      insertion_points:
        volumes: present    # overlay/sidecar mount anchor
        entrypoint: absent  # sidecar invoke anchor (#40886 install entrypoint dropped — AWQ keys native in v0.22.0)
  vllm/qwen-a3b-preview-single:
    compose_path: models/qwen3.6-35b-a3b/vllm/compose/single/autoround-int4/preview.yml
    genesis_equipped: false
    genesis_equipped_evidence: no GENESIS_* token in compose and kv_format is not turboquant*
    compose_service_template:
      source: models/qwen3.6-35b-a3b/vllm/compose/single/autoround-int4/preview.yml  # whole service definition captured verbatim from this file
      param_slots:
        ports: { source: E.default_port, value: 8050 }
        tensor_parallel_size: { token: '${TP}', source: E.tp, value: 1 }
        max_model_len: { token: '${MAX_MODEL_LEN}', source: E.max_ctx, value: 8192 }
        gpu_memory_utilization: { token: '${GPU_MEMORY_UTILIZATION}', source: E.mem_util, value: 0.92 }
        kv_cache_dtype: { token: '${KV_CACHE_DTYPE}', source: 'kv_arg(E.kv_format)', kv_format: fp8_e5m2, value: 'fp8_e5m2' }
        max_num_seqs: { token: '--max-num-seqs', source: E.max_num_seqs, value: 1 }
        speculative_config: omitted  # E.drafter is None -> --speculative-config not emitted
      governed_slots:
        trust_remote_code:
          token: '--trust-remote-code'
          present_in_shipped_compose: true
          policy: governed   # locked design v6 §88 security model
          emit_rule: 'only if arch trc gate resolves evidence-cited false-permitted; never blind-passthrough'
      constants:
        image: '${VLLM_IMAGE:-vllm/vllm-openai:nightly-${VLLM_NIGHTLY_SHA}}'   # captured constant; engine pin flows via env, NOT rewritten
        verbatim_from_compose: [shm_size, ipc, deploy.resources, model_cache_volume, base_environment, base_entrypoint, '--model', '--served-model-name', '--quantization', '--dtype', '--tool-call-parser', '--chat-template', '--reasoning-parser', '--default-chat-template-kwargs', '--enable-prefix-caching', '--enable-chunked-prefill', '--enforce-eager']
      insertion_points:
        volumes: present    # overlay/sidecar mount anchor
        entrypoint: absent  # sidecar invoke anchor
  vllm/qwen-35b-a3b-dual:
    compose_path: models/qwen3.6-35b-a3b/vllm/compose/dual/autoround-int4/fp8.yml
    genesis_equipped: false
    genesis_equipped_evidence: no GENESIS_* token in compose and kv_format is not turboquant*
    compose_service_template:
      source: models/qwen3.6-35b-a3b/vllm/compose/dual/autoround-int4/fp8.yml  # whole service definition captured verbatim from this file
      param_slots:
        ports: { source: E.default_port, value: 8051 }
        tensor_parallel_size: { token: '${TP}', source: E.tp, value: 2 }
        max_model_len: { token: '${MAX_MODEL_LEN}', source: E.max_ctx, value: 262144 }
        gpu_memory_utilization: { token: '${GPU_MEMORY_UTILIZATION}', source: E.mem_util, value: 0.92 }
        kv_cache_dtype: { token: '${KV_CACHE_DTYPE}', source: 'kv_arg(E.kv_format)', kv_format: fp8_e5m2, value: 'fp8_e5m2' }
        max_num_seqs: { token: '--max-num-seqs', source: E.max_num_seqs, value: 1 }
        speculative_config: omitted  # E.drafter is None -> --speculative-config not emitted
      governed_slots:
        trust_remote_code:
          token: '--trust-remote-code'
          present_in_shipped_compose: true
          policy: governed   # locked design v6 §88 security model
          emit_rule: 'only if arch trc gate resolves evidence-cited false-permitted; never blind-passthrough'
      constants:
        image: '${VLLM_IMAGE:-vllm/vllm-openai:v0.22.0}'   # captured constant; engine pin flows via env, NOT rewritten
        verbatim_from_compose: [shm_size, ipc, deploy.resources, model_cache_volume, base_environment, base_entrypoint, '--model', '--served-model-name', '--quantization', '--dtype', '--tool-call-parser', '--chat-template', '--reasoning-parser', '--default-chat-template-kwargs', '--enable-prefix-caching', '--enable-chunked-prefill', '--enforce-eager']
      insertion_points:
        volumes: present    # overlay/sidecar mount anchor
        entrypoint: absent  # sidecar invoke anchor

# --------------------------------------------------------------------------
# Phase A-prime fold-in: arch -> model_slugs + trust-remote-code precision.
#   Keyed by the same `arch:` string used in arch_patches.yml. `model_slugs`
#   are the compose_registry `model` values served by that arch on this
#   stack. `trust_remote_code` is derived from each listed model's OWN
#   config.json on /mnt/models/huggingface (auto_map absent + no *modeling*.py
#   modeling file shipped with the weights => false, evidence-cited). Generic
#   common-transformers lower-bound rows have no on-stack weights to inspect
#   => model_slugs [] and trust_remote_code stays unverified (honest: nothing
#   to cite). arch_patches.yml is the C0 authority for requires_trust_remote_code;
#   this block is the evidence ledger the generator's step-5 trc gate reads to
#   decide the governed-slot emission. The two MUST agree for in-scope arches.
# --------------------------------------------------------------------------
arch_model_xref:
  Qwen3NextForCausalLM:
    family: qwen3-next-hybrid
    model_slugs: [qwen3.6-27b]
    trust_remote_code: false
    trust_remote_code_evidence: "qwen3.6-27b weights config.json (qwen3.6-27b-autoround-int4) has architectures=[Qwen3_5ForConditionalGeneration], auto_map absent, no *modeling*.py modeling file shipped with weights -> loads built-in transformers/vLLM class, no remote code execution"
    golden_triple_profiles: [vllm/minimal, vllm/dual]
  Qwen3_5MoeForConditionalGeneration:
    family: qwen3-next-moe
    model_slugs: [qwen3.6-35b-a3b]
    trust_remote_code: false
    trust_remote_code_evidence: "qwen3.6-35b-a3b weights config.json (qwen3.6-35b-a3b-autoround-int4) has architectures=[Qwen3_5MoeForConditionalGeneration], auto_map absent, no *modeling*.py shipped -> built-in class"
  Gemma4ForConditionalGeneration:
    family: gemma4-swa-dense
    model_slugs: [gemma-4-31b]
    trust_remote_code: false
    trust_remote_code_evidence: "gemma-4-31b weights config.json (gemma-4-31b-autoround-int4) has architectures=[Gemma4ForConditionalGeneration], auto_map absent, no *modeling*.py shipped -> built-in class"
    golden_triple_profiles: [vllm/gemma-bf16-mtp, vllm/gemma-int8-mtp, vllm/gemma-mtp-tp1]
  Gemma4ForCausalLM:
    family: gemma4-swa-dense
    model_slugs: []
    trust_remote_code: unverified
    trust_remote_code_evidence: none   # no on-stack model uses this exact text-only arch string; brief requires deriving from the model's OWN config -> nothing to cite
  Gemma4ForConditionalGenerationMoE:
    family: gemma4-swa-moe
    model_slugs: [gemma-4-26b-a4b]
    trust_remote_code: false
    trust_remote_code_evidence: "gemma-4-26b-a4b weights config.json (gemma-4-26b-a4b-autoround-int4-mixed AND gemma-4-26b-a4b-awq-4bit) both have architectures=[Gemma4ForConditionalGeneration], auto_map absent, no *modeling*.py shipped -> built-in class"
  LlamaForCausalLM:
    family: dense
    model_slugs: []
    trust_remote_code: unverified
    trust_remote_code_evidence: none   # generic common-transformers lower-bound row, no on-stack weights to inspect
  MistralForCausalLM:
    family: dense
    model_slugs: []
    trust_remote_code: unverified
    trust_remote_code_evidence: none
  Qwen2ForCausalLM:
    family: dense
    model_slugs: []
    trust_remote_code: unverified
    trust_remote_code_evidence: none
  Qwen3ForCausalLM:
    family: dense
    model_slugs: []
    trust_remote_code: unverified
    trust_remote_code_evidence: none
  Phi3ForCausalLM:
    family: dense
    model_slugs: []
    trust_remote_code: unverified
    trust_remote_code_evidence: none
  Gemma2ForCausalLM:
    family: dense
    model_slugs: []
    trust_remote_code: unverified
    trust_remote_code_evidence: none