# frank-archon.env — radiance (StillDeadcode) on BOTH R9700s (TP=2),
# Dankserver :7770, publisher's 4-bit-codebook container of the official
# Qwen3.8-Flash-Next.
#
# ONE OWNER: shape, payload identity, eras, laws and every measured number live
# in serverAppConfigs-docs/LLM/frank-archon.md. This file carries the knobs plus
# only the reason a reader editing THIS line cannot recover from the page.
# Where the two disagree, this file wins on values; the boot ledger arbitrates
# the engine shape.
FRANK_ARCHON_IMAGE=stilldeadcode/radiance@sha256:4c3f484564bb2872784e46b0a59cbd71becc9c1e746e301a3596ffae253c322e
# 1.0.13 is pinned by digest on purpose: 1.2.0 is a DEAD END on this payload
# (acceptance 0.7123 vs 0.7549 — the page's Dead ends section names the suspect).
# The .rad file mounted under /models; /data holds the prefix-cache disk tier.
# The model dir holds ONLY .rad files — the HF download and staging stay beside it.
FRANK_ARCHON_MODEL_DIR=/home/dank/models/rad
FRANK_ARCHON_MODEL_FILE=qwen3.8-next-flash-fp8-iq4r-moe.rad
FRANK_ARCHON_STATE_DIR=/home/dank/radiance-state
# state dir's tune/ subdir carries rad-tune's kernel-selection cache; the engine
# reads $RADIANCE_HOME/tune/<machine>.tune and that defaults to /opt/radiance
# (inside the image), so the cache only survives on a host mount.
# Container identity is the SERVICE name: one name across systemctl and
# `podman ps`; the runtime changes, the name does not. The legacy list retires
# every predecessor identity that could hold the GPUs or the port.
FRANK_ARCHON_CONTAINER=frank-archon
FRANK_ARCHON_LEGACY_CONTAINERS="frank-archon-qwen frank-archon-r9v qwen-fp8 glm-probe"
# Served id. Radiance VALIDATES the requested model name, so every client must
# send exactly this value (unlike llama.cpp and halogen, which ignore it).
FRANK_ARCHON_SERVED_NAME=frank-archon
FRANK_ARCHON_PORT=7770
# Frank's chat-template call: froggeric's fixed Qwen3.8 template, vendored in
# the repo; it overrides the template baked into the .rad, and radiance derives
# the reasoning and tool-call reply format from it.
FRANK_ARCHON_TEMPLATE=/home/dank/serverAppConfigs/scripts/qwen38-froggeric-v22.5.jinja

# --- engine shape (the boot ledger arbitrates every number below) ---------
# TP=2 needs the 2026-09-20 board (x8/x8 on root ports): a collective cannot be
# dispatched on a card whose PCIe chain lacks atomics. Radiance's wire is
# libr4d's own, not RCCL.
FRANK_ARCHON_TP=2
# Lossy WHT 6-bit wire for large all-reduces (publisher's production choice). It
# stays EXACT for single-sequence decode and any step of <= 25 rows — see
# MAX_SEQS x (1 + SPEC_TOKENS) below.
FRANK_ARCHON_TP_WIRE=wht6
# Decode slots. A slot costs KV, never decode; the pool is sized to this
# contract and nothing more, so a FOURTH full-height conversation is REFUSED as
# too large to fit — never squeezed, paged or truncated. That is Frank's
# explicit trade: the freed MiB went to the expert slab.
FRANK_ARCHON_MAX_SEQS=3
# Served window. The engine treats `kv group tokens >= max-model-len` as a HARD
# limit, and models.yml contextWindow MUST quote this number (over-length is a
# refusal, not a truncation). The pool is sized for seqs x maxlen, not one
# sequence.
FRANK_ARCHON_MAX_MODEL_LEN=200000
FRANK_ARCHON_PLACEMENT=expert_tiered
# Pinned host pool for expert rows that do not fit VRAM. It moves WITH
# VRAM_WEIGHTS: the pair and this pool serve the per-rank resident set together,
# so cutting the slab spills here — under-sizing it is a boot failure (36,864
# refused a boot). The ledger's coverage line is the referee, not this file.
FRANK_ARCHON_HOST_POOL_MIB=44928
# VRAM left unclaimed per card (publisher default 96 MiB); the engine's settle
# floor is built from it.
FRANK_ARCHON_GPU_HEADROOM_MIB=96
# ONE budget per card: VRAM_WEIGHTS + VRAM_KV <= 30,969 MiB, the ceiling the
# engine's own budget table prints (derivation and the slab/pool price: the
# page's VRAM laws). Idle KV VRAM is ALSO the expert cache's spillover, so a
# bigger pool pays twice — which is why the pool sits at the contract and the
# slab takes the rest.
FRANK_ARCHON_VRAM_WEIGHTS_MIB=25600
FRANK_ARCHON_VRAM_KV_MIB=5120
# fp8 is the ONLY rung below bf16 on this engine: one kv_dtype for the whole
# cache, so llama.cpp's exact-K/quantized-V split (frank-zealot) is unservable
# here. bf16 costs 1.89x fp8, not 2x — the QSA block-key plane is dtype-fixed.
FRANK_ARCHON_KV_DTYPE=fp8
# The checkpoint's own MTP head at depth 2: this fleet's ladder was measured at
# 2, and 3 x (1+2) = 9 rows stays inside the wht6 25-row exactness bound.
FRANK_ARCHON_SPEC_TOKENS=2
FRANK_ARCHON_MAX_BATCHED_TOKENS=2048
# Prefix cache tiers. The host tier is sized in ENTRIES and one entry tracks the
# cache dtype (58.50 KiB at fp8), so a dtype change re-sizes the parked set
# without touching these numbers.
FRANK_ARCHON_PREFIX_HOST_MIB=8192
FRANK_ARCHON_PREFIX_DISK_MIB=65536
# Frank's pin law: the PLE n-gram table serves from pinned host RAM the cards
# read. `ram` REFUSES the start if memlock is too small — the unit's
# LimitMEMLOCK=infinity is the other half of this law.
FRANK_ARCHON_NGRAM_PLACEMENT=ram
# TTM preflight. The pinned ledger (~147 GiB) rides TTM's shared pages, and the
# kernel RESETS pages_limit to half of RAM on every boot; below the plan the
# load dies mid-pin with an anonymous allocator error. ttm-preflight.sh raises
# the knob itself before refusing by name, so recovery is a boot, not a visit.
FRANK_ARCHON_TTM_MIN_MIB=150000
FRANK_ARCHON_TTM_TARGET_MIB=204800
# Escape hatch for experiments. Unset -> no extra argv; the serve script expands
# this unquoted on purpose, so keep multi-flag values as one string.
FRANK_ARCHON_EXTRA_ARGS=
# Deployer gate: a truncated fetch must be a fast refusal, not a long-timeout
# boot. Floor sits under the live payload and under every rollback payload
# (see the page's Eras table for what is on disk and what needs a re-download).
FRANK_ARCHON_RAD_MIN_MIB=110000