# frank-primary.env — tcclaviger RDNA4 vLLM production config (dankserver :7770).
#
# 2026-10-01 cutover to the BF16-KV no-spec incumbent (the overnight redo
# campaign's verdict, Frank's call): same digest-pinned engine and payload as
# the 2026-09-29 cutover, but the KV cache is UNQUANTIZED (auto = bf16) and
# speculative decode is GONE. Git tag frank-primary-fp8-mtp-20261001 is the
# last pre-cutover commit; the old shape (fp8 KV + MTP4) is in history and
# restorable from the tag.
#
# Every number here was QUALIFIED by boot probe on 2026-10-01 (not inherited):
#   * MAXLEN 241664 x SEQS 3 (724,992 tokens) at bf16 KV is the DEPLOYED
#     shape (2026-10-01 night ladder): KV_BYTES 10,184,000,000 PER RANK,
#     engine measured "KV cache size: 732,359 tokens; Maximum concurrency
#     for 241,664 tokens per request: 3.03x". 262144 and 245760 both OOMed
#     at graph capture (76 MiB short / 0 bytes free); 237568 passed at
#     718,606 tokens and the +4096 bonus step passed and won.
#   * KV_BYTES is PER RANK. The old "7.2 GiB ceiling, 9/16 GiB OOM" law was
#     the MTP4 WORKSPACE: the spec-era pool measured 729,545 tokens because
#     the drafter reserved ~2.6 GiB/rank beside the pool. No-spec bf16 takes
#     11.05 GiB/rank and boots clean — the ceiling was spec's, not VRAM's.
#   * bf16 KV doubles the attention-KV bytes/token (measured 14,047 vs
#     7,926) and costs ~14% decode vs fp8 at 4064 ctx (49.25 -> 36.42 with
#     the gather win) — traded deliberately for clean cache + 262k windows.
#   * GATHER 32x64 is the night's biggest lever: R4D_LRU_GATHER_CHUNKS=32 /
#     R4D_LRU_GATHER_LANES=64 measured +18.7% decode vs default geometry,
#     and the win grows with depth (39.5@166 -> 54.1@1087 -> 49.3@4064 fp8
#     era). Do not drop it.
#   * MNBT 1024 is Frank's lock: MNBT 512 doubles TTFT at 4064 ctx (2.46 s
#     vs 1.36 s); 1024-4096 are interchangeable on decode; 12288 costs 2.5%
#     and arena. 1024 keeps the workspace floor so the arena stays max.
#   * PREFETCH IS ABSENT BY LAW: expert-cache telemetry measured the
#     prefetcher at 36% precision (36,720 slabs prefetched, 13,369 served) —
#     roughly half the gather traffic was waste. Never re-add
#     --expert-prefetch without a fresh A/B.
#   * TunableOp stays OFF: CLAV_TUNABLEOP_SWEEP silently skips under expert
#     offload unless CLAV_TUNABLEOP_WITH_OFFLOAD=1, and forcing it corrupts
#     numerics.
#
# HIP reads bare env vars TEMP, HOST, GPU_MAX_HEAP_SIZE — every key here is
# prefixed FRANK_PRIMARY_ so none can leak.
#

# --- runtime ----------------------------------------------------------------
# Digest-pinned: the floating :latest tag moved once already. Local alias
# qwen-fp8-runtime:tuned-20260929 (image ID 3322dbbbc96d) points at the same
# bytes in rootless storage.
FRANK_PRIMARY_IMAGE=docker.io/tcclaviger/vllm@sha256:da4029666668b90a0386c1ed23ea370c79916ad4e1a6ad1dd9db098b9fa069ea

# --- payload ----------------------------------------------------------------
FRANK_PRIMARY_MODEL_DIR=/home/dank/models/Qwen3.8-Flash-Next-Uncensored-FP8
FRANK_PRIMARY_MODEL_SHARDS=131

# --- identity ---------------------------------------------------------------
# The harness models.yml id stays frank-primary (provider 192.168.0.235:7770).
FRANK_PRIMARY_CONTAINER=frank-primary-qwen
FRANK_PRIMARY_SERVED_NAME=frank-primary
FRANK_PRIMARY_PUBLISH=7770:7770
# Containers removed before every start: the retired R9V identity and the ad
# hoc experiment identity (both hold the GPUs / name registrations).
FRANK_PRIMARY_LEGACY_CONTAINERS="frank-primary-r9v qwen-fp8"

# --- qualified engine shape (2026-10-01, final: 3 windows + max arena) --------
# SEQS 3 x MAXLEN 262144 at fp8 KV (Frank's call, 2026-10-01): three contexts
# of the model's FULL native window, with the KV pool pinned to the FLOOR the
# contract needs so that everything else goes to the expert ARENA — the
# remainder is what the fork's planner gives the decode-critical expert cache.
#   3 x 262144 = 786,432 tokens; measured fp8 rate 7,698 B/token (from the
#   4-slot boot: 8,311,013,376 B -> 1,079,582 tokens, and the 5-slot boot:
#   10,388,766,720 B -> 1,350,182 tokens) => 6.054e9 B is the floor. Pinned at
#   6,100,000,000 => ~792k tokens, a ~5.9k-token margin, and ~2.2 GiB returned
#   to the arena versus the 4-slot shape.
# History in this shape: 5 x 262144 booted (KV 1,350,182 / 5.15x) but left 0
# bytes free and a real request (995-token prompt, max_tokens=261149) killed
# the worker; 4 x 262144 (KV 1,079,582 / 4.12x) was the runtime-survivable
# stopgap. Six full-length contexts never fit (6 x 241664 asked 10.70 GiB
# against 9.18 GiB free).
# MNBT 2048 (Frank's call): the arena sweep measured it at the same 6,499-slot
# ceiling as <=4096, so the bigger batch costs the arena nothing.
FRANK_PRIMARY_MAXLEN=262144
FRANK_PRIMARY_SEQS=3
FRANK_PRIMARY_KV_BYTES=6100000000
FRANK_PRIMARY_KV_DTYPE=fp8
FRANK_PRIMARY_MNBT=2048
FRANK_PRIMARY_GATHER_CHUNKS=32
FRANK_PRIMARY_GATHER_LANES=64
FRANK_PRIMARY_UTIL=0.98

# --- client contract: reasoning split, tools, preserve_thinking ----------------
# Without --reasoning-parser the engine leaves the thinking text INLINE in
# `content` with a dangling `</think>` and a null `reasoning` field (measured
# 2026-10-01: content = 'We need answer...Brief.\n</think>\n\n391') — the
# malformed thinking block clients choke on. The qwen3 parser splits it
# properly. The GLM rollback (d91379d) had dropped all three of these; the
# working values are the ones ecaad36 shipped for this model.
FRANK_PRIMARY_REASONING_PARSER=qwen3
# Tools: --enable-auto-tool-choice + the qwen3_xml parser is what makes
# tool_calls work here (without it, tool_choice auto returns 400).
FRANK_PRIMARY_TOOL_PARSER=qwen3_xml
# preserve_thinking keeps prior thinking blocks in the rendered prompt across
# turns; enable_thinking makes thinking the server-side default. Verified the
# payload's tokenizer_config template consumes both keys.
FRANK_PRIMARY_CHAT_TEMPLATE_KWARGS='{"enable_thinking": true, "preserve_thinking": true}'