# Tunables for frank-medium (ajgazin/Swift-Qwen3.8-27B-Uncensored-Dynamic-MTP
# UD-Q8_K_XL + z-lab/Qwen3.8-27B-DFlash2-GGUF Q8_0 drafter), mainline llama.cpp
# on Dankserver, 2x AMD Radeon AI PRO R9700 (gfx1201).  Since 2026-09-16 this
# is the SOLE LLM runtime on the box: the vllm-radiance replica pair and its
# routing proxy are retired.
#
# Hardware: two R9700 (Navi 48, RDNA4, 32,624 MiB each), no XGMI, different
# IOMMU groups -- every cross-card byte goes over PCIe.  The Raphael iGPU
# (gfx1036/Radeon 610M) enumerates as HIP device 2 and is hidden below so
# nothing can drift onto shared system RAM.
#
# WHY LAYER SPLIT AND NOT TENSOR (operator call, 2026-09-16): tensor parallel
# needs a cross-card allreduce per layer, and this host cannot dispatch one.
# RCCL's kernels carry a hidden hostcall-buffer parameter, and ROCr refuses it
# on a device without PCIe atomics -- the second card sits behind the B650
# chipset bridges (AtomicOpsCap: Routing-, read-only), so every collective that
# touches it dies with hipErrorIllegalState.  Measured on this box 2026-09-15
# (llama-bench, pp4096 / tg128, f16 KV, fa on):
#
#   single R9700    1160.9 / 19.42
#   layer  2x       1991.2 / 18.76      (859.1 / 17.64 at depth 32768)
#   tensor 2x        271.8 / 26.26      (no RCCL: butterfly fallback, -7x prefill)
#
# Layer split distributes layers in order; only the activation at the boundary
# crosses the wire, once per forward pass.  That is the "pipeline parallelism"
# this service wanted, and it needs no collective at all.
#
# Runtime: mainline llama.cpp master fb27a525 (2026-09-16), gfx1201, built by
# scripts/build-llama-rdna4.sh against a private ROCm 7.14.0a20260624 toolchain
# that is bundled next to the binary (RPATH $ORIGIN/../lib, no LD_LIBRARY_PATH).
# The ref is pinned by TWO features: DFlash2 (ggml-org/llama.cpp#27342 -- the
# drafter is detected from its GGUF) and qwen35 MTP.  Do not float it.
#
# Model: ajgazin/Swift-Qwen3.8-27B-Uncensored-Dynamic-MTP-GGUF @ UD-Q8_K_XL,
# 29.29 GiB, arch qwen35, Unsloth Dynamic 3.0 (per-tensor types from Unsloth's
# own quant of the same size, on Unsloth's importance matrix).  Abliteration is
# orcarouter's single refusal direction projected out of 131 tensors; the vision
# tower is untouched but unused here (text only, see NO_MMPROJ).  The file also
# carries the model's MTP head (blk.64.nextn.*), so a file-level switch to
# --spec-type draft-mtp is available without a second copy in VRAM.
#
# Drafter: z-lab/Qwen3.8-27B-DFlash2-GGUF @ Q8_0, 1.92 GiB: 5 layers, hidden
# 5120, block-diffusion proposal with the candidate selector.  Decoding stays
# lossless -- the target verifies every drafted token.
#
# Architecture (GGUF arch qwen35): 64 layers as 16 x (3 x (Gated DeltaNet ->
# FFN) + 1 x (Gated Attention -> FFN)) -- 48 linear-attention layers whose
# per-sequence state is CONSTANT-SIZE, 16 full-attention layers at 4 KV heads x
# 256 head_dim.  A token therefore costs 2 x 4 x 256 x 2 B = 64 KiB of KV at f16
# in the attention layers only, plus ~0.16 GiB per sequence of f32 DeltaNet
# state at any depth.
#
# SIZING, measured (rocm-smi, 2026-09-16).  Weights split across the two cards;
# the drafter rides the second.  The loader's compute buffers are part of what
# is seen below -- they are allocated at load, not per request:
#
#   CTX_SIZE   GPU 0        GPU 1        headroom on the busier card
#   131072     19.89 GB     24.30 GB     9.9 GB / 31 %
#   262144     24.72 GB     29.14 GB     5.07 GB / 15 %   <- deployed
#
# 262144 is the window the model ships (n_ctx_train) and it fits with room, so
# the fleet gets the whole thing; the arithmetic that used to cap this endpoint
# at 114688 was the vLLM predecessor's, not this runtime's.  If a future change
# adds VRAM (a longer drafter, quantized KV, more slots) re-read the numbers
# rather than assuming, and prefer CTX_SIZE over --gpu-layers.
#
# WARNING: do not name any variable TEMP, HOST, or GPU_MAX_HEAP_SIZE (HIP reads
# those bare vars; 2026-08-13 incident).  llama.cpp takes --host/--port/--temp
# as flags only.

# llama-server: mainline fb27a525 built for gfx1201 by scripts/build-llama-rdna4.sh.
LLAMA_BIN=/home/dank/GitPackages/llama.cpp-dflash2/build-rdna4-rocm714/bin/llama-server

# Payload, fetched with scripts/download-frank-medium-gguf.sh.
MODEL_DIR=/home/dank/models/Swift-Qwen3.8-27B-Uncensored-Dynamic-MTP-GGUF
MODEL_FILE=Swift-Qwen3.8-27B-Uncensored-Dynamic-MTP-UD-Q8_K_XL.gguf
DRAFT_MODEL_DIR=/home/dank/models/Qwen3.8-27B-DFlash2-GGUF
DRAFT_MODEL_FILE=Qwen3.8-27B-DFlash2-Q8_0.gguf

# Fleet identity.  7770 is the fleet's dankserver endpoint; the alias is the id
# at /v1/models and what every client asks for.
ALIAS=frank-medium
BIND_ADDR=0.0.0.0
LISTEN_PORT=7770
# Device placement.  HIP_VISIBLE_DEVICES hides the Raphael iGPU (HIP device 2)
# so nothing can drift onto shared system RAM; DEVICES is what llama.cpp splits
# across, and neither of the two cards has an XGMI link to the other.
HIP_VISIBLE_DEVICES=0,1
DEVICES=ROCm0,ROCm1
SPLIT_MODE=layer
# Empty = distribute layers by free VRAM (equal here, so 1,1 by hand).
TENSOR_SPLIT=1,1

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

# One slot at the model's full configured window (n_ctx_train 262144), which was
# measured to fit before it was deployed: see SIZING above.  --parallel DIVIDES
# --ctx-size between slots, so one slot carries the whole window and a second
# concurrent request queues behind it.
CTX_SIZE=262144
PARALLEL=1

BATCH_SIZE=2048
UBATCH_SIZE=512

# Threads cover tokenization, sampling and HTTP only: every layer is on a GPU.
NUM_THREADS=8
THREAD_BATCH=8

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

# Sampling defaults for requests that send none -- the values the vLLM
# predecessor served on this endpoint (`--override-generation-config`), so a
# client sees no change across the runtime swap.  The model card's own
# recommendation is temp 1.0 / top_p 0.95; the harness sets its own per model in
# models.yml, so this is the floor, not the contract.
TEMPERATURE=0.7
TOP_P=0.95
TOP_K=20
MIN_P=0.0
PRESENCE_PENALTY=0.0

# Reasoning on, projected into reasoning_content (deepseek format) with no
# budget: the model decides how long to think.
REASONING=on
REASONING_FORMAT=deepseek
REASONING_BUDGET=-1

# Chat template: empty = the one embedded in the GGUF (Qwen3.8's own).
CHAT_TEMPLATE_FILE=
CHAT_TEMPLATE_KWARGS='{"enable_thinking":true,"preserve_thinking":true}'

# Speculative decoding: the DFlash2 block-diffusion drafter.  Its GGUF carries
# block_size 8, so at most 7 draft tokens per verification step (llama.cpp
# asserts n_max <= block_size - 1); 7 is also what the drafter was published
# with.  The drafter rides ROCm1, the card that ends up holding the target's
# last layers -- the hidden states the proposal consumes.
SPEC_TYPE=draft-dflash
SPEC_DRAFT_N_MAX=7
SPEC_DRAFT_NGL=999
SPEC_DRAFT_DEVICE=ROCm1
SPEC_DRAFT_TYPE_K=f16
SPEC_DRAFT_TYPE_V=f16

# Text only: the server must not autoload a vision tower.  Vision stays on
# frank-small (Dankclaw, RTX 3090), which is the fleet's image endpoint.
NO_MMPROJ=1