# frank-large — gufo (gufo-org/gufo) serving
# Swift-1.5-Qwen3.8-27B-Uncensored (abliterated) on the Strix Halo iGPU.
#
# These are the tunables read by scripts/serve-frank-large.sh. The flag
# list is owned by the serve script; this file only sets fleet values.
#
# DO NOT name a new tunable TEMP, HOST or GPU_MAX_HEAP_SIZE: the HIP
# runtime reads those bare (the 2026-08-13 TEMP incident). HOST is the one
# exception because the serve script itself consumes it for --host.

# The target payload (scripts/download-frank-large-q4.sh): the serve script
# refuses to start without the main GGUF and the DFlash2 drafter.
#
# 2026-10-01 swap (Frank): unsloth/Qwen3.8-27B-GGUF:UD-Q4_K_XL, 16.35 GiB,
# replacing ajgazin's abliterated Swift-1.5 UD-Q8_K_XL (29.3 GiB). Two
# consequences worth knowing at a glance:
#   * this is the VANILLA (non-abliterated) Qwen3.8-27B — the endpoint is no
#     longer uncensored, which was one of the reasons the Swift payload was
#     chosen on 2026-09-28;
#   * ~13 GiB of weights became available for KV, which is what makes four
#     full-sized f16 sessions fit.
# gufo needs no template for either: its Qwen renderer is compiled in.
MODEL_DIR=/home/dank/models/Qwen3.8-27B-UD-Q4_K_XL
MODEL_FILE=/home/dank/models/Qwen3.8-27B-UD-Q4_K_XL/Qwen3.8-27B-UD-Q4_K_XL.gguf

# The DFlash2 drafter is UNCHANGED by the model swap and still lives beside
# the previous target, so it carries its own directory. It has a sliding
# window of 2048, which is what keeps its KV small (~40 MiB).
DRAFTER_DIR=/home/dank/models/Qwen3.8-27B-UD-Q8_K_XL
DRAFTER_FILE=/home/dank/models/Qwen3.8-27B-UD-Q8_K_XL/Qwen3.8-27B-DFlash2-Q4_K_M.gguf

# The gufo runtime, built from source by scripts/build-gufo.sh.
RUNTIME_DIR=/home/dank/GitPackages/gufo-v0.1.1

# Fleet endpoint: the same port and alias every frank-large has served, so
# no client, probe or models.yml entry changes address.
ALIAS=frank-large
HOST=0.0.0.0
PORT=7770

# Four sessions, 163840 context each (Frank, 2026-10-01: "4x 160k"). The
# context is per session and the KV is UNQUANTIZED (f16) — gufo has no KV
# quantization lever at all (execution_policy.hpp pins kv_cache_storage to
# kFp16), so "unquantized" is inherent rather than configured.
#
# The arithmetic that makes this fit: f16 KV costs 64 KiB/token on this model
# (16 full-attention layers x 4 KV heads x 256 head_dim x 2 (K,V) x 2 bytes;
# the other 48 layers are linear-attention with a per-SEQUENCE fp32 state of
# ~144 MiB, not a per-token cache). 4 x 163840 = 655,360 tokens = 40.0 GiB of
# KV, and each session's 163,840 tokens is exactly 10 GiB. Budget: weights
# 16.35 + KV 40.0 + drafter 1.07 + linear state 0.56 + runtime ~4 = ~62 GiB
# against the 114 GiB GTT — roughly 50 GiB of headroom, so the session count
# or the per-session context can both grow from here.
CONTEXT_SIZE=163840
SESSIONS=4

# DFlash2 spec decode (a block-diffusion drafter). gufo sizes the draft
# block itself; DRAFT_TOKENS caps the proposals per step (gufo's default is
# 7, chosen over llama.cpp's fixed depth 4 because gufo's adaptive policy
# shortens the block when acceptance drops) and DRAFT_POLICY is the block
# length controller.
DRAFT_TOKENS=7
DRAFT_POLICY=adaptive