# frank-zealot — llama.cpp (PrismML fork build 10777, CUDA) on the RTX 3090,
# :7771. Payload: Ternary-Bonsai-2-9B PQ2_0 with the MTP head in the file.
#
# ONE OWNER: shape, payload identity, eras, laws and every measured number
# live in serverAppConfigs-docs/LLM/frank-zealot.md. This file carries the
# knobs and only the reason a reader editing THIS line cannot recover
# elsewhere. Where the two disagree, this file wins on values.
LLAMA_BIN=/home/dank/GitPackages/llama-prism-b10777/llama-server
# The fork is a LOCK, not a preference: custom tensor type 142 + prism.hadamard.*
# metadata. Stock llama.cpp refuses the file; a loader ignoring the Hadamard
# metadata dequantizes wrong, silently.
MODEL_FILE=/home/dank/models/Bonsai2-9B-MTP/Ternary-Bonsai-2-9B-PQ2_0-MTP-Q8_0.gguf
# Q8_0 IS MANDATORY: the publisher states the BF16 tower can crash llama-server
# under concurrent image requests, which is exactly --parallel 2.
MMPROJ_FILE=/home/dank/models/Bonsai2-9B-MTP/Ternary-Bonsai-2-9B-mmproj-Q8_0.gguf
# Served id — the harness/family name, not a fact about the payload.
# Id-keyed consumers: OpenWebUI (model row, access_grant, api_configs), models.yml.
ALIAS=frank-zealot
BIND_ADDR=0.0.0.0
LISTEN_PORT=7771
# CTX_SIZE is the POOL llama.cpp divides across slots: 524,288 / 2 = 262,144 a
# conversation, each still at the trained window. MUST stay divisible by
# PARALLEL (the seam enforces it) and models.yml contextWindow quotes the
# PER-SLOT number — a longer prompt is a 400, never a truncation. The pool
# cannot go back to 786,432 under exact f16 KV: 24,576 MiB of cache against the
# 24,123 MiB the driver leaves addressable, before a weight loads.
CTX_SIZE=524288
PARALLEL=2
BATCH_SIZE=4096
# Ubatch is a prefill knob (decode never moves with it) and it sets the
# compute-buffer size — which is what decides whether a drafter fits.
# UBATCH_SIZE=1024 is the documented MTP arm.
UBATCH_SIZE=2048
# Exact K and V: the retrieval-fidelity ask, paid with one conversation of
# concurrency. Rate law and the arithmetic: [[frank-zealot]] → Laws.
CACHE_TYPE_K=f16
CACHE_TYPE_V=f16
# Speculation OFF — measured, not assumed: the draft context bills its own f16
# KV over the WHOLE pool, and there is no room beside exact KV (the arm census
# is on the page). SPEC_TYPE=none strips the WHOLE set (--spec-type and every
# --spec-draft-*); half a set has segfaulted at load.
SPEC_TYPE=none
SPEC_DRAFT_N_MAX=2
SPEC_DRAFT_N_MIN=0
SPEC_DRAFT_P_MIN=0
# The sampler recipe lives in the checkpoint (general.sampling.*) and
# llama.cpp reads it itself. Presence penalty is the one recipe value with no
# GGUF metadata key, so it must reach argv. "" is the documented opt-out.
PRESENCE_PENALTY=1.0
NGL=99
# 4 = debug: KV layout, buffer sizes and graph capture land in the journal, and
# that is what VRAM forensics read. Above 4 floods the journal.
VERBOSITY=4
# Without --metrics llama.cpp answers 501 on /metrics, which Prometheus reads
# as DOWN while /health stays 200. 0 opts out and re-breaks the scrape.
METRICS=1