# 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