# Tunables for frank-medium (kingjones777/Qwen3.8-27B-ROCmFPX-Q8_0-AGENT-GGUF,
# charlie12345/ROCmFPX llama.cpp, Dankserver, 2x AMD Radeon AI PRO R9700).
#
# Hardware (2026-09-15): the RTX 3090 left Dankserver and two Radeon AI PRO
# R9700 cards (Navi 48, gfx1201, RDNA4, 32,624 MiB each, PCIe 5.0 x16) took
# its place.  The Raphael iGPU (gfx1036) is still enumerated by HIP as the
# third device.  There is no XGMI link between the two cards and they sit in
# different IOMMU groups, so any cross-GPU traffic goes over PCIe.
#
# Runtime: charlie12345/ROCmFPX (llama.cpp fork, ROCmFPX quant family; the
# Q8_0_ROCMFPX_AGENT tensor type exists nowhere else - stock llama.cpp cannot
# load this GGUF).  Built for gfx1201 with the fork's self-contained ROCm
# 7.14 toolchain so the host's stale /opt/rocm-6.3.3 install is never used:
#
#   cd /home/dank/GitPackages/charlie-ROCmFPX
#   env JOBS=8 ./scripts/build-rocmfp4-rocm714-local.sh
#
# gfx1201 must be the build target: a gfx1200 binary links, loads the model
# and then segfaults on this card (fork's docs/BUILD-AMD-ARCHITECTURES.md).
#
# Model: kingjones Qwen3.8-27B-ROCmFPX-Q8_0-AGENT - Q8_0_ROCMFPX_AGENT
# (ftype 115), 26.28 GiB, 8.39 bpw, arch qwen35 (MoE), quantized from a
# 51.3 GiB BF16 source.  The AGENT routing keeps 12 more attention-output
# projections at full Q8_0 than the plain 8-bit build, which buys a higher
# MTP draft acceptance (0.953 vs 0.911) and that is the whole point of this
# checkpoint.  Model card documents 131,072 context.
#
# Parallelism (--split-mode layer, operator call 2026-09-15 "pipeline
# parallelism"): layers are distributed across the two cards in order and
# activations hop PCIe at the boundary.  Measured with llama-bench
# (pp4096 / tg128 / same at depth 32768, f16 KV, fa on, 3 reps):
#
#   single R9700   1160.9 / 19.42   (fits: 26.27 GiB weights, ~5 GiB left)
#   layer  2x      1991.2 / 18.76   859.1 / 17.64
#   tensor 2x       271.8 / 26.26   228.6 / 25.09
#
# Tensor parallel wins decode (+40 %) but collapses prefill 7x: this build
# has no RCCL (llama.cpp logs "AllReduce init failed; falling back to
# meta-backend butterfly"), so every layer pays a slow cross-card reduction.
# Agentic traffic is prefill-heavy, so layer split wins the workload.  Revisit
# if the fork ships a working RCCL tensor path.
#
# WARNING: do not name any variable TEMP, HOST, or GPU_MAX_HEAP_SIZE. The
# ROCm HIP runtime reads those bare env vars (see the 2026-08-13 TEMP
# incident).  llama.cpp reads --host/--port/--temp as CLI flags, never as
# env vars.

# charlie12345/ROCmFPX llama-server (self-contained ROCm 7.14 build, RPATH
# points at the bundled runtime libs; no LD_LIBRARY_PATH needed).
LLAMA_BIN=/home/dank/GitPackages/charlie-ROCmFPX/build-rdna4-rocm714/bin/llama-server

# Model package, fetched with scripts/download-q8agent.sh:
#   Qwen3.8-27B-Q8_0_ROCMFPX_AGENT.gguf   26.28 GiB  main weights
#   mtp-Qwen3.8-27B-Q4_0.gguf              1.68 GiB  MTP draft head
#   mmproj-Qwen3.8-27B-BF16.gguf           0.93 GiB  vision tower (unused)
MODEL_DIR=/home/dank/models/kingjones-Qwen3.8-27B-ROCMFPX-Q8_0-AGENT
MODEL_FILE=Qwen3.8-27B-Q8_0_ROCMFPX_AGENT.gguf
DRAFT_MODEL_FILE=mtp-Qwen3.8-27B-Q4_0.gguf

# Alias + network.  The port is the fleet's dankserver endpoint; the alias is
# what clients ask for, and it replaces the retired `frank-small`.
ALIAS=frank-medium
BIND_ADDR=0.0.0.0
LISTEN_PORT=7770

# Device placement.  HIP_VISIBLE_DEVICES hides the iGPU (device 2) so nothing
# can drift onto shared system RAM; DEVICES is what llama.cpp splits across.
HIP_VISIBLE_DEVICES=0,1
DEVICES=ROCm0,ROCm1
SPLIT_MODE=layer

# TENSOR_SPLIT empty = layers distributed by free VRAM (equal here).
TENSOR_SPLIT=

NGL=999
# Auto-fit has no business resizing a context we set explicitly.
FIT=off
FLASH_ATTN=on

# 131,072 tokens, one slot (the model card's documented window; the GGUF
# reports n_ctx_train 262144, untested by the model author).  Layer split
# keeps each layer's KV on the card that owns the layer, so the window is
# bounded by per-card free memory: ~5.6 GiB of KV per card at 131072 f16.
CTX_SIZE=131072
PARALLEL=1

# 26.28 GiB of weights + MTP draft + KV cache leaves ~15 GiB per card at this
# context, so the batch shape is chosen for prefill throughput, not memory.
BATCH_SIZE=2048
UBATCH_SIZE=512
NUM_THREADS=8
THREAD_BATCH=8

# f16 K/V: an agent checkpoint is the wrong place to spend KV precision.
CACHE_TYPE_K=f16
CACHE_TYPE_V=f16
CTX_CHECKPOINTS=8
CACHE_RAM=8192

# Sampling: the checkpoint's instruct table.
TEMPERATURE=0.7
TOP_P=0.8
TOP_K=20
MIN_P=0.0
PRESENCE_PENALTY=1.5

# Reasoning on; DeepSeek format projects the trace into reasoning_content
# instead of literal thinking tags in content.
REASONING=on
REASONING_FORMAT=deepseek
REASONING_BUDGET=-1

# Chat template: empty = the template embedded in the GGUF.  Point this at
# /home/dank/serverAppConfigs/scripts/chat-template.jinja to force the repo's
# Sharp agent template instead.
CHAT_TEMPLATE_FILE=
CHAT_TEMPLATE_KWARGS='{"enable_thinking":true,"preserve_thinking":true}'

# MTP speculative decoding.  n_max 6 / p_min 0.6 is the fork's measured
# sweet spot for a MTP head with high acceptance; p_min 0.0 drafts
# low-probability tokens that get rejected and makes MTP a net loss.
SPEC_TYPE=draft-mtp
SPEC_DRAFT_N_MAX=6
SPEC_DRAFT_N_MIN=0
SPEC_DRAFT_P_MIN=0.6
SPEC_DRAFT_P_SPLIT=0.10
SPEC_DRAFT_NGL=999
SPEC_DRAFT_TYPE_K=f16
SPEC_DRAFT_TYPE_V=f16
SPEC_DRAFT_POLL=1
SPEC_DRAFT_POLL_BATCH=1
# The draft head rides the card that holds the target model's LAST layers:
# the MTP head consumes the final hidden state, so pinning it to ROCm1 keeps
# the per-token hop off the wire.  (Under the abandoned tensor split the
# draft must also be pinned to exactly one device or the meta-device KV
# allocation aborts: GGML_ASSERT(buffer) in ggml-backend.cpp, measured
# 2026-09-15.)
SPEC_DRAFT_DEVICE=ROCm1