gen-seat: deploy Qwen3.8-27B-Uncensored gen seat, rename qwen36-27b-aeon->gen-seat

- New uncensored gen seat: JonathanColetti/Qwen3.8-27B-Uncensored, in-house NVFP4
  W4A16 (compressed-tensors) + grafted bf16 MTP (config ignore re:^mtp.*), vision-intact,
  262K ctx, MTP n=3 (~42% accept, ~68 tok/s). Replaces the qwen3.6-35b-a3b-heretic MoE.
- Rename compose project qwen36-27b-aeon -> gen-seat, container vllm-aeon-gen -> vllm-gen,
  env vars AEON_GEN_* -> GEN_*; drop the dormant vllm-aeon-rp service.
- litellm: repoint 7 aliases (gen/summarizer/summarizer-large/classifier/image-judge/
  qwen-image-bench -> qwen3.8-27b-uncensored; gen-reasoning -> -thinking).
- servers/ana-ml2/README: refresh the gen hero-seat row.

servers/ana-ml2/README.md

@@ -41,7 +41,7 @@ embed/rerank/reward trio. GPUs are pinned per container via
 
 | Container | Port | Served model | Quant | Ctx |
 |-----------|------|--------------|-------|-----|
-| `vllm-aeon-gen` | 8015 | `qwen3.6-35b-a3b-heretic` — the "gen" hero seat | NVFP4 (modelopt) | 256k |
+| `vllm-gen` (project `gen-seat`) | 8015 | `qwen3.8-27b-uncensored` — the "gen" hero seat (Qwen3.8-27B Heretic-abliterated, in-house NVFP4 W4A16 + grafted MTP) | NVFP4 W4A16 (compressed-tensors) | 262k |
 | `vllm-charrp-reasoning-nvfp4` | 8018 | `char-rp-reasoning` (R36 reasoning RP) | NVFP4 (modelopt) | 256k |
 
 **GPU 1 — light / eval / retrieval + char-RP GGUF (~91/98 GB, on-demand):**
@@ -91,7 +91,7 @@ Latest snapshot: `system-details.txt` (regenerate as needed).
 Every seat is explicitly pinned via `device_ids` (no unpinned containers), and
 both cards run ~90% full:
 
-- **GPU 0:** the two heavy NVFP4 seats — `vllm-aeon-gen` (gen) and
+- **GPU 0:** the two heavy NVFP4 seats — `vllm-gen` (gen) and
   `vllm-charrp-reasoning-nvfp4`. The live serving path (near-100% util under
   load), ~42 + 45 GB.
 - **GPU 1:** everything else — summarizer (granite), judge (selene), reward,

stacks/gen-seat/.env.example

@@ -0,0 +1,18 @@
+# gen-seat tunables — fleet `gen` seat (ana-ml2 GPU 0, :8015). Edit here, never commit.
+GEN_IMAGE=vllm/vllm-openai:latest
+API_KEY=
+GEN_GPU_ID=0
+
+GEN_CONTAINER_NAME=vllm-gen
+GEN_PORT=8015
+GEN_SERVED_NAME=qwen3.8-27b-uncensored
+GEN_SERVED_NAME_THINK=qwen3.8-27b-uncensored-thinking
+GEN_MODEL=/tank/aimodels/qwen38-27b-uncensored-nvfp4
+GEN_QUANT=compressed-tensors
+GEN_GPU_MEM_UTIL=0.45
+GEN_MAX_MODEL_LEN=262144
+GEN_MAX_NUM_SEQS=16
+GEN_KV_CACHE_DTYPE=fp8
+GEN_REASONING_PARSER=qwen3
+GEN_SPEC_METHOD=qwen3_5_mtp
+GEN_SPEC_TOKENS=3

stacks/gen-seat/compose.yaml

@@ -0,0 +1,97 @@
+# gen-seat — the fleet's general `gen` seat on ana-ml2 GPU 0 (:8015).
+# Serves JonathanColetti/Qwen3.8-27B-Uncensored (Heretic abliteration KL 0.12, vision-intact
+# Qwen3_5ForConditionalGeneration, grafted MTP head), quantized in-house to NVFP4 W4A16
+# (compressed-tensors) with the bf16 MTP grafted back. ⚠ the grafted MTP requires
+# `re:^mtp.*` in config.json quantization_config.ignore or vLLM loads it uninitialized (0% accept).
+# Backs gateway aliases: gen, gen-reasoning, summarizer, summarizer-large, classifier,
+# image-judge, qwen-image-bench (all via api_base :8015).
+#
+# Two served-names (base + `-thinking`): LiteLLM keys deployments by (model, api_base), so gen
+# and gen-reasoning use distinct names to avoid the shared-config enable_thinking clobber.
+# --mamba-cache-dtype float32 for the GDN/hybrid-linear-attn state; MTP via qwen3_5_mtp n=3;
+# full 262K context (hybrid attention -> cheap KV, ~8.6GB at 262K). All tunables in .env.
+# (Renamed from qwen36-27b-aeon/vllm-aeon-gen; dormant RP service dropped 2026-08-15.)
+
+name: gen-seat
+
+services:
+  vllm-gen:
+    image: ${GEN_IMAGE:-vllm/vllm-openai:latest}
+    container_name: ${GEN_CONTAINER_NAME:-vllm-gen}
+    restart: unless-stopped
+    ipc: host
+    ports:
+      - "${GEN_PORT:-8015}:8000"
+    volumes:
+      - /tank/aimodels/huggingface:/hfcache
+      - ${GEN_MODEL:-/tank/aimodels/qwen38-27b-uncensored-nvfp4}:/model:ro
+    environment:
+      - HF_HOME=/hfcache
+      - HF_HUB_CACHE=/hfcache/hub
+      - VLLM_API_KEY=${API_KEY:-}
+      - PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True
+    command:
+      - /model
+      - --served-model-name
+      - ${GEN_SERVED_NAME:-qwen3.8-27b-uncensored}
+      - ${GEN_SERVED_NAME_THINK:-qwen3.8-27b-uncensored-thinking}
+      - --host
+      - 0.0.0.0
+      - --port
+      - "8000"
+      - --quantization
+      - ${GEN_QUANT:-compressed-tensors}
+      - --gpu-memory-utilization
+      - ${GEN_GPU_MEM_UTIL:-0.45}
+      - --max-model-len
+      - ${GEN_MAX_MODEL_LEN:-262144}
+      - --max-num-seqs
+      - ${GEN_MAX_NUM_SEQS:-16}
+      - --max-num-batched-tokens
+      - "16384"
+      - --trust-remote-code
+      - --dtype
+      - auto
+      - --mamba-cache-dtype
+      - float32
+      - --kv-cache-dtype
+      - ${GEN_KV_CACHE_DTYPE:-fp8}
+      - --enable-prefix-caching
+      - --enable-chunked-prefill
+      - --limit-mm-per-prompt
+      - '{"image": 4}'
+      - --reasoning-parser
+      - ${GEN_REASONING_PARSER:-qwen3}
+      - --enable-auto-tool-choice
+      - --tool-call-parser
+      - qwen3_coder
+      - --speculative-config
+      - '{"method": "${GEN_SPEC_METHOD:-qwen3_5_mtp}", "num_speculative_tokens": ${GEN_SPEC_TOKENS:-3}}'
+    deploy:
+      resources:
+        reservations:
+          devices:
+            - driver: nvidia
+              device_ids:
+                - "${GEN_GPU_ID:-0}"
+              capabilities:
+                - gpu
+    healthcheck:
+      test: ["CMD", "curl", "-f", "http://localhost:8000/health"]
+      interval: 30s
+      timeout: 10s
+      retries: 3
+      start_period: 900s
+    networks:
+      - tnet
+    labels:
+      - homepage.group=AI - Inference
+      - homepage.name=Qwen3.8-27B Uncensored (NVFP4, vision, MTP) — gen
+      - homepage.icon=mdi-creation
+      - homepage.description=Uncensored Qwen3.8-27B multimodal NVFP4+MTP, the `gen` seat (ana-ml2 GPU 0)
+      - homepage.href=http://10.250.50.54:${GEN_PORT:-8015}/docs
+
+networks:
+  tnet:
+    name: traefik-net
+    external: true

stacks/litellm/conf/config.yaml

@@ -22,44 +22,51 @@ model_list:
   #     R15 P03 eval). vLLM on ana-ml2 GPU 1, official FP8, 50K ctx. Explicit
   #     entry shadows the "*" wildcard's llama-swap route for this name. Full
   #     prompt + completion captured per call. ---
-  - model_name: granite-4.1-8b
+  # --- granite-4.1-8b RETIRED 2026-08-12 (seat downed, GPU1 reclaimed for RP context) ---
-    litellm_params:
+#   - model_name: granite-4.1-8b
-      model: hosted_vllm/granite-4.1-8b
+#     litellm_params:
-      api_base: http://10.250.50.54:8004/v1
+#       model: hosted_vllm/granite-4.1-8b
-      api_key: os.environ/VLLM_API_KEY
+#       api_base: http://10.250.50.54:8004/v1
-      temperature: 0
+#       api_key: os.environ/VLLM_API_KEY
-    model_info:
+#       temperature: 0
-      mode: chat
+#     model_info:
+#       mode: chat
 
-  # alias: summarizer -> granite-4.1-8b (operator 2026-06-19). Duplicate-entry alias
+  # alias: summarizer -> gen (repointed 2026-08-12, granite retired) (operator 2026-06-19). Duplicate-entry alias
   #   (not router_settings.model_group_alias — that's hidden from /v1/models and can be
   #   silently ignored in config per litellm #15020/#5524). Keep api_base in sync above.
   - model_name: summarizer
     litellm_params:
-      model: hosted_vllm/granite-4.1-8b
+      model: hosted_vllm/qwen3.8-27b-uncensored
-      api_base: http://10.250.50.54:8004/v1
+      api_base: http://10.250.50.54:8015/v1
       api_key: os.environ/VLLM_API_KEY
       temperature: 0
+      extra_body:
+        chat_template_kwargs:
+          enable_thinking: false
     model_info:
       mode: chat
 
-  # alias: classifier -> granite-4.1-8b (operator 2026-06-19). Light/fast classification
+  # alias: classifier -> gen (repointed 2026-08-12, granite retired) (operator 2026-06-19). Light/fast classification
   #   + triage endpoint; same backend as summarizer. Keep api_base in sync above.
   - model_name: classifier
     litellm_params:
-      model: hosted_vllm/granite-4.1-8b
+      model: hosted_vllm/qwen3.8-27b-uncensored
-      api_base: http://10.250.50.54:8004/v1
+      api_base: http://10.250.50.54:8015/v1
       api_key: os.environ/VLLM_API_KEY
       temperature: 0
+      extra_body:
+        chat_template_kwargs:
+          enable_thinking: false
     model_info:
       mode: chat
 
-  # alias: summarizer-large -> gen / qwen3.6-35b-a3b-heretic (operator 2026-07-05). For heavier
+  # alias: summarizer-large -> gen / qwen3.8-27b-uncensored (operator 2026-07-05). For heavier
   #   summarization that wants the 35B-A3B heretic `gen` model instead of granite-8b. Thinking OFF
   #   (matches gen). Keep api_base (:8015) + enable_thinking in sync with the gen record below.
   - model_name: summarizer-large
     litellm_params:
-      model: hosted_vllm/qwen3.6-35b-a3b-heretic
+      model: hosted_vllm/qwen3.8-27b-uncensored
       api_base: http://10.250.50.54:8015/v1
       api_key: os.environ/VLLM_API_KEY
       presence_penalty: 1.5
@@ -75,14 +82,14 @@ model_list:
   # --- image-judge / qwen-image-bench — T2I quality JUDGE aliases. The dedicated
   #     Qwen-Image-Bench NVFP4 backend (ana-ml2 GPU 1, :8014) was RETIRED 2026-07-15
   #     (operator: reclaim ~30GB GPU1) after the arbo→gen hero-judge switch. Both
-  #     aliases now REPOINT to the gen backend (:8015, qwen3.6-35b-a3b-heretic,
+  #     aliases now REPOINT to the gen backend (:8015, qwen3.8-27b-uncensored,
   #     vision-intact), held at deterministic judge sampling (temp 0 / top_k 1) with
   #     enable_thinking:false (a reasoning preamble breaks json_object). Revert =
   #     `docker compose start` stacks/qwen-image-bench on ana-ml2 + repoint api_base
   #     back to :8014 + model hosted_vllm/qwen-image-bench. ---
   - model_name: qwen-image-bench
     litellm_params:
-      model: hosted_vllm/qwen3.6-35b-a3b-heretic
+      model: hosted_vllm/qwen3.8-27b-uncensored
       api_base: http://10.250.50.54:8015/v1
       api_key: os.environ/VLLM_API_KEY
       temperature: 0
@@ -96,7 +103,7 @@ model_list:
       mode: chat
   - model_name: image-judge
     litellm_params:
-      model: hosted_vllm/qwen3.6-35b-a3b-heretic
+      model: hosted_vllm/qwen3.8-27b-uncensored
       api_base: http://10.250.50.54:8015/v1
       api_key: os.environ/VLLM_API_KEY
       temperature: 0
@@ -114,7 +121,7 @@ model_list:
   #     Displaced AEON-27B 2026-07-08 (which had displaced qwopus3.5-122b 2026-07-05). MoE 35B-A3B
   #     (256 experts / 8 active), qwen3_5_moe GDN-hybrid, native MTP preserved but served MTP-OFF
   #     (spec-decode hurts concurrent aggregate). Served on :8015 via vLLM,
-  #     served-name qwen3.6-35b-a3b-heretic. Thinking split = chat_template_kwargs.enable_thinking +
+  #     served-name qwen3.8-27b-uncensored. Thinking split = chat_template_kwargs.enable_thinking +
   #     --reasoning-parser qwen3; tool-calling qwen3_coder. gen / gen-reasoning + summarizer-
   #     large route here; -reasoning enables thinking. Keep api_base (:8015) in sync.
   #     RETIRED with the displacement (→ 404, callers migrate to gen): qwen3.5-122-a10b
@@ -126,7 +133,7 @@ model_list:
   #     GENERAL thinking profile, not the 0.6 coding sub-profile). docs/pfi/model-sampler-defaults.md. ---
   - model_name: gen
     litellm_params:
-      model: hosted_vllm/qwen3.6-35b-a3b-heretic
+      model: hosted_vllm/qwen3.8-27b-uncensored
       api_base: http://10.250.50.54:8015/v1
       api_key: os.environ/VLLM_API_KEY
       presence_penalty: 1.5
@@ -142,7 +149,7 @@ model_list:
     litellm_params:
       # Distinct served-name so a thinking-off `gen` request can't mutate this deployment's
       # enable_thinking (shared-config-mutation footgun). Same backend :8015, different model id.
-      model: hosted_vllm/qwen3.6-35b-a3b-heretic-thinking
+      model: hosted_vllm/qwen3.8-27b-uncensored-thinking
       api_base: http://10.250.50.54:8015/v1
       api_key: os.environ/VLLM_API_KEY
       presence_penalty: 1.5
@@ -167,7 +174,7 @@ model_list:
   #   docs/pfi/model-sampler-defaults.md.
   - model_name: char-rp
     litellm_params:
-      model: hosted_vllm/magidonia-24b-v4.3
+      model: hosted_vllm/char-rp
       api_base: http://10.250.50.54:8016/v1
       api_key: os.environ/VLLM_API_KEY
       temperature: 1.1
@@ -248,9 +255,7 @@ model_list:
       top_p: 0.9
     model_info:
       mode: chat
-  # reranker → generic capability name for rerank. Repointed to bge-reranker-v2-m3
+  # reranker → generic capability name for rerank (currently qwen3-reranker).
-  # 2026-08-06 (Brokkr R43: incumbent Qwen3-Reranker-0.6B harmed 80/90 fleet queries;
-  # boundary 17:37:48Z). Incumbent stays reachable via the qwen3-reranker alias for rollback.
   - model_name: reranker
     litellm_params:
       model: hosted_vllm/BAAI/bge-reranker-v2-m3

stacks/qwen36-27b-aeon/.env.example

@@ -1,53 +0,0 @@
-# qwen36-27b-aeon tunables — copy to .env on the host, edit there (never commit .env).
-# The real .env lives at /opt/docker/compose/qwen36-27b-aeon/.env on ana-ml2.
-
-# Per-service vLLM image. Both on latest (0.24.0) after validating it on rp. Reasoning works
-# on 0.24.0 (and did on 0.23.0 too — the trace bug was a LiteLLM shared-config mutation, not
-# vLLM). Rollback: set either back to vllm/vllm-openai:known-good-0.23.0 (tagged on the host).
-AEON_GEN_IMAGE=vllm/vllm-openai:latest
-AEON_RP_IMAGE=vllm/vllm-openai:latest
-
-# Shared vLLM API key (matches the litellm VLLM_API_KEY). Blank = no auth.
-API_KEY=
-
-# Both instances pin to the same physical GPU (the freed qwopus slot).
-AEON_GPU_ID=0
-
-# ── General serve (MTP off) → gen / gen-reasoning / summarizer-large ──
-AEON_GEN_CONTAINER_NAME=vllm-aeon-gen
-AEON_GEN_PORT=8015
-AEON_GEN_SERVED_NAME=qwen3.6-27b-aeon
-AEON_GEN_SERVED_NAME_THINK=qwen3.6-27b-aeon-thinking
-AEON_GEN_MODEL=/tank/aimodels/qwen36-27b-aeon-nvfp4
-# NOTE: live gen serves qwen3.6-35b-a3b-heretic since 2026-07-08 (aeon-27b displaced);
-# SERVED_NAME/MODEL above lag live — pending reconciliation with the model swap.
-# util/ctx/seqs RE-TUNED 2026-07-16 (char-rp left GPU-0 → room): util 0.30->0.42,
-# ctx 131072->262144 (256K native), seqs 16->32. gen MoE KV is cheap → 5.43x @ 256K.
-AEON_GEN_GPU_MEM_UTIL=0.42
-AEON_GEN_MAX_MODEL_LEN=262144
-AEON_GEN_MAX_NUM_SEQS=32
-AEON_GEN_KV_CACHE_DTYPE=fp8
-# Reasoning parser — KEEP qwen3. This checkpoint's chat_template.jinja injects the opening
-# <think> into the PROMPT (output has only </think>). qwen3 handles the non-thinking path
-# correctly. NOTE: enable_thinking:true does NOT surface reasoning_content under EITHER qwen3
-# or deepseek_r1 (the reasoning is generated but dropped) — that needs a chat_template fix,
-# NOT a parser swap. deepseek_r1 was tested and is WORSE: it breaks the non-thinking path
-# too (both content and reasoning_content come back empty). Do not use deepseek_r1 here.
-AEON_GEN_REASONING_PARSER=qwen3
-
-# ── RP seat (native MTP on) → char-rp ──
-AEON_RP_CONTAINER_NAME=vllm-aeon-rp
-AEON_RP_PORT=8016
-AEON_RP_SERVED_NAME=qwen3.6-27b-aeon-rp
-AEON_RP_SERVED_NAME_THINK=qwen3.6-27b-aeon-rp-thinking
-# Full 27GB variant by default; switch to the 21GB XS for ~6GB more co-location margin:
-#   AEON_RP_MODEL=/tank/aimodels/qwen36-27b-aeon-nvfp4-xs
-AEON_RP_MODEL=/tank/aimodels/qwen36-27b-aeon-nvfp4
-AEON_RP_GPU_MEM_UTIL=0.40
-AEON_RP_MAX_MODEL_LEN=65536
-AEON_RP_MAX_NUM_SEQS=2
-AEON_RP_KV_CACHE_DTYPE=fp8
-AEON_RP_REASONING_PARSER=qwen3
-# Native MTP head. If stock vLLM names it differently, try method=mtp.
-AEON_RP_SPEC_METHOD=qwen3_5_mtp
-AEON_RP_SPEC_TOKENS=3

stacks/qwen36-27b-aeon/compose.yaml

@@ -1,214 +0,0 @@
-# qwen36-27b-aeon — AEON-7/Qwen3.6-27B-AEON-Ultimate-Uncensored on ana-ml2 GPU 0,
-# REPLACING qwopus3.5-122b as the `gen` model (operator 2026-07-05).
-#
-# Dense 27B, qwen3_5 GDN-hybrid arch (full-attn + Gated DeltaNet SSM) — same family
-# as qwopus, VISION-INTACT (Qwen3_5ForConditionalGeneration, vision tower preserved
-# at bf16), abliterated (abliterix v1.4, 0/100 refusals), native MTP head grafted,
-# Apache-2.0, 131K default ctx. Served NVFP4 (ModelOpt) on Blackwell's FP4 cores.
-#
-# TWO CO-LOCATED INSTANCES on GPU 0 (operator wants both behaviours resident at once;
-# MTP is a serve-time config, NOT per-request, so one endpoint can't do both):
-#   vllm-aeon-gen (:8015, served qwen3.6-27b-aeon)    — MTP OFF, general/concurrent
-#       serve. Backs gateway gen / gen-reasoning / summarizer-large.
-#   vllm-aeon-rp  (:8016, served qwen3.6-27b-aeon-rp) — native MTP ON (qwen3_5_mtp
-#       n=3), low-concurrency single-seat RP. Backs gateway char-rp.
-# Why MTP off for the general serve: measured on qwopus, MTP helps single-stream
-# (+12% N=1) but HURTS moderate concurrency (-15..-20% N=4) and silently drops
-# min_p/logit_bias — wrong for a shared multi-consumer endpoint. Right only for a
-# dedicated single-stream seat (the RP one). [[reference_gen_qwopus_122b]]
-#
-# VRAM budget (2 weight copies, no sharing): full NVFP4 = 27GB ea. gen util 0.45
-# (~43GB) + rp util 0.40 (~38GB) = ~81GB / 96GB, ~15GB margin. depends_on:
-# service_healthy sequences gen-first so the util reservation doesn't race → OOM.
-# If margin bites at warmup (vision-encoder + big-vocab sampler warmup, cf. qwen36-vl),
-# point AEON_RP_MODEL at the 21GB XS variant (frees ~6GB) via .env — no compose edit.
-#
-# NVFP4 is ModelOpt format → --quantization modelopt (vLLM also auto-detects; explicit
-# is belt-and-suspenders). --mamba-cache-dtype float32 for the GDN/SSM state (AEON
-# deploy guide + vLLM recipe Mamba-cache note). Tool-calling qwen3_coder + reasoning
-# qwen3 (per the AEON card), same as qwopus.
-#
-# ⚠️ DEPLOYABILITY — load-test before trusting: multimodal + ModelOpt-NVFP4 on THIS
-# brand-new arch, and native qwen3_5_mtp spec-decode, are unproven on our stock vLLM
-# image. If stock can't serve it, the AEON patched image (ghcr.io/aeon-7/aeon-vllm-
-# ultimate, PRs #41703/#40898) is the fallback — but that's really for DFlash; native
-# MTP + base inference should ride stock >= 0.23.0. Set AEON_IMAGE in .env.
-#
-# REVERT: `docker compose down` here + `docker compose up -d` the qwopus3.5-122b stack
-# (still staged) + revert the litellm gen/gen-reasoning/summarizer-large records.
-# All tunables in .env — edit that, not this file.
-
-name: qwen36-27b-aeon
-
-services:
-  # ── General serve — MTP OFF, concurrent. gen / gen-reasoning / summarizer-large. ──
-  vllm-aeon-gen:
-    # Per-service image so gen can stay pinned to a known-good vLLM while rp tests a new one.
-    image: ${AEON_GEN_IMAGE:-vllm/vllm-openai:latest}
-    container_name: ${AEON_GEN_CONTAINER_NAME:-vllm-aeon-gen}
-    restart: unless-stopped
-    ipc: host
-    ports:
-      - "${AEON_GEN_PORT:-8015}:8000"
-    volumes:
-      - /tank/aimodels/huggingface:/hfcache
-      - ${AEON_GEN_MODEL:-/tank/aimodels/qwen36-27b-aeon-nvfp4}:/model:ro
-    environment:
-      - HF_HOME=/hfcache
-      - HF_HUB_CACHE=/hfcache/hub
-      - VLLM_API_KEY=${API_KEY:-}
-      # Reclaims PyTorch reserved-but-unallocated fragmentation so the co-located
-      # util split doesn't strand VRAM (same knob qwopus needed for the MoE workspace).
-      - PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True
-    command:
-      - /model
-      # TWO served-names: base + a `-thinking` alias. LiteLLM keys deployments by
-      # (model, api_base), so gen and gen-reasoning MUST use distinct model names or a
-      # thinking-off request mutates the shared litellm_params and clobbers the other's
-      # enable_thinking (the shared-config-mutation footgun). gen-reasoning routes to the
-      # `-thinking` name; gen/summarizer-large route to the base name.
-      - --served-model-name
-      - ${AEON_GEN_SERVED_NAME:-qwen3.6-27b-aeon}
-      - ${AEON_GEN_SERVED_NAME_THINK:-qwen3.6-27b-aeon-thinking}
-      - --host
-      - 0.0.0.0
-      - --port
-      - "8000"
-      - --quantization
-      - modelopt
-      - --gpu-memory-utilization
-      - ${AEON_GEN_GPU_MEM_UTIL:-0.45}
-      - --max-model-len
-      - ${AEON_GEN_MAX_MODEL_LEN:-131072}
-      # Keep concurrency modest: big-vocab sampler warmup allocates a large tensor
-      # (qwen36-vl OOM'd at the default 1024 on a shared GPU). 16 is ample here.
-      - --max-num-seqs
-      - ${AEON_GEN_MAX_NUM_SEQS:-16}
-      - --max-num-batched-tokens
-      - "16384"
-      - --trust-remote-code
-      - --dtype
-      - auto
-      # GDN/SSM (Gated DeltaNet) state cache — float32 per the AEON deploy guide.
-      - --mamba-cache-dtype
-      - float32
-      - --kv-cache-dtype
-      - ${AEON_GEN_KV_CACHE_DTYPE:-fp8}
-      - --enable-prefix-caching
-      - --enable-chunked-prefill
-      - --limit-mm-per-prompt
-      - '{"image": 4}'
-      - --reasoning-parser
-      - ${AEON_GEN_REASONING_PARSER:-qwen3}
-      - --enable-auto-tool-choice
-      - --tool-call-parser
-      - qwen3_coder
-    deploy:
-      resources:
-        reservations:
-          devices:
-            - driver: nvidia
-              device_ids:
-                - "${AEON_GPU_ID:-0}"
-              capabilities:
-                - gpu
-    healthcheck:
-      test: ["CMD", "curl", "-f", "http://localhost:8000/health"]
-      interval: 30s
-      timeout: 10s
-      retries: 3
-      start_period: 900s
-    networks:
-      - tnet
-    labels:
-      - homepage.group=AI - Inference
-      - homepage.name=Qwen3.6-27B AEON (NVFP4, vision) — gen
-      - homepage.icon=mdi-creation
-      - homepage.description=Uncensored Qwen3.6-27B multimodal NVFP4, the `gen` model (ana-ml2 GPU 0)
-      - homepage.href=http://10.250.50.54:${AEON_GEN_PORT:-8015}/docs
-
-  # ── RP seat — native MTP ON, low concurrency, single-seat. char-rp. ──
-  vllm-aeon-rp:
-    image: ${AEON_RP_IMAGE:-vllm/vllm-openai:latest}
-    container_name: ${AEON_RP_CONTAINER_NAME:-vllm-aeon-rp}
-    restart: unless-stopped
-    ipc: host
-    # Sequence AFTER the general serve is healthy so the two util reservations on the
-    # shared GPU don't race into an OOM (gen reserves its 0.45 first, then rp its 0.40).
-    depends_on:
-      vllm-aeon-gen:
-        condition: service_healthy
-    ports:
-      - "${AEON_RP_PORT:-8016}:8000"
-    volumes:
-      - /tank/aimodels/huggingface:/hfcache
-      # Point at the XS (21GB) variant via .env to buy ~6GB co-location margin.
-      - ${AEON_RP_MODEL:-/tank/aimodels/qwen36-27b-aeon-nvfp4}:/model:ro
-    environment:
-      - HF_HOME=/hfcache
-      - HF_HUB_CACHE=/hfcache/hub
-      - VLLM_API_KEY=${API_KEY:-}
-      - PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True
-    command:
-      - /model
-      # base + `-thinking` alias (see the gen note): char-rp -> base, char-rp-reasoning -> -thinking.
-      - --served-model-name
-      - ${AEON_RP_SERVED_NAME:-qwen3.6-27b-aeon-rp}
-      - ${AEON_RP_SERVED_NAME_THINK:-qwen3.6-27b-aeon-rp-thinking}
-      - --host
-      - 0.0.0.0
-      - --port
-      - "8000"
-      - --quantization
-      - modelopt
-      - --gpu-memory-utilization
-      - ${AEON_RP_GPU_MEM_UTIL:-0.40}
-      - --max-model-len
-      - ${AEON_RP_MAX_MODEL_LEN:-65536}
-      # Single-seat: low concurrency keeps warmup + KV small so it fits alongside gen.
-      - --max-num-seqs
-      - ${AEON_RP_MAX_NUM_SEQS:-2}
-      - --trust-remote-code
-      - --dtype
-      - auto
-      - --mamba-cache-dtype
-      - float32
-      - --kv-cache-dtype
-      - ${AEON_RP_KV_CACHE_DTYPE:-fp8}
-      - --enable-prefix-caching
-      - --limit-mm-per-prompt
-      - '{"image": 4}'
-      - --reasoning-parser
-      - ${AEON_RP_REASONING_PARSER:-qwen3}
-      # Native MTP speculative decode (the grafted head). n=3 per the AEON card's
-      # measured accept length (~3.3/3). MTP is why this seat exists separately.
-      - --speculative-config
-      - '{"method": "${AEON_RP_SPEC_METHOD:-qwen3_5_mtp}", "num_speculative_tokens": ${AEON_RP_SPEC_TOKENS:-3}}'
-    deploy:
-      resources:
-        reservations:
-          devices:
-            - driver: nvidia
-              device_ids:
-                - "${AEON_GPU_ID:-0}"
-              capabilities:
-                - gpu
-    healthcheck:
-      test: ["CMD", "curl", "-f", "http://localhost:8000/health"]
-      interval: 30s
-      timeout: 10s
-      retries: 3
-      start_period: 900s
-    networks:
-      - tnet
-    labels:
-      - homepage.group=AI - Dormant
-      - homepage.name=Qwen3.6-27B AEON RP (NVFP4 + MTP) — char-rp
-      - homepage.icon=mdi-drama-masks
-      - homepage.description=Uncensored Qwen3.6-27B, native MTP single-seat RP (char-rp), ana-ml2 GPU 0
-      - homepage.href=http://10.250.50.54:${AEON_RP_PORT:-8016}/docs
-
-networks:
-  tnet:
-    name: traefik-net
-    external: true