# frank-primary.env — tunables for the vLLM 0.30 frank-primary endpoint
# (Qwen3.8-Flash-Next-FP8, 2x R9700 gfx1201, dankserver :7770).
#
# Paths and numbers only — NEVER credentials. Do not name a tunable TEMP, HOST
# or GPU_MAX_HEAP_SIZE: the HIP runtime reads those bare names (2026-08-13).
#
# Container paths: the model tree is mounted at /models (host
# /home/dank/models); the compile caches live under /cache (host
# /home/dank/.cache/frank-primary-vllm, keyed on model + stack + graph knobs —
# never share it across configurations).

# --- identity ---------------------------------------------------------------
SERVED_NAME=frank-primary
BIND_HOST=0.0.0.0
PORT=7770

# --- model ------------------------------------------------------------------
# Host-side dir: /home/dank/models/Qwen3.8-Flash-Next-FP8 (131 safetensors
# shards, 172.78 GiB, verified against model.safetensors.index.json).
MODEL_DIR=/models/Qwen3.8-Flash-Next-FP8

# --- placement --------------------------------------------------------------
# Fixed 2-card tensor parallel (the R9700 pair; the Raphael iGPU is index 2
# and excluded by the visibility pins).
ROCR_VISIBLE_DEVICES=0,1
HIP_VISIBLE_DEVICES=0,1
TP=2
# 0.97 of 31.86 GiB/card (34,208,743,424 B) — leaves ~1 GiB for the ROCm
# baseline. Raise only with a measured reason.
GPU_UTIL=0.97
# The model's native window.
CTX_SIZE=262144
# Sequences the scheduler may hold. 8 is the proven batch shape on this host
# (radiance era); revisit with a bench after bring-up.
MAX_SEQS=8

# --- weight offloading (the UVA shape) ---------------------------------------
# --offload-backend uva: matched weights live in PINNED host RAM and are read
#   in place over PCIe by the kernels (zero-copy), instead of being resident
#   on the cards. is_uva_available() = is_pin_memory_available() on ROCm; the
#   pin needs the unit's LimitMEMLOCK=infinity (a root unit grants it via
#   PID1 — the dankserver user session defaults to 8 MiB and cannot raise it).
#   If pinning is unavailable the offloader falls back to a copy path — the
#   load log MUST be checked for the UVA path, not just /health.
# --cpu-offload-gb is PER GPU (GiB). 2x R9700 total pinned budget ≈ 160 GiB of
#   the 246 GiB host RAM; the rest covers the OS, llama.cpp-era page cache
#   drain and the pinned staging buffers. Do not raise without checking
#   MemAvailable at load time.
# --cpu-offload-params: name SEGMENTS (dot-delimited components) of tensors
#   to offload. Measured from the payload headers (2026-09-26): `ple` matches
#   138 tensors = 131 n-gram table shards + 7 per-layer conv/proj weights,
#   47.75 GiB; `experts` matches 150,528 tensors, 114.86 GiB. Combined
#   162.60 GiB — with TP=2 each rank needs ~81.3 GiB of pinned host RAM,
#   hence OFFLOAD_GB=82 per GPU (164 GiB total; 80/card left 2.6 GiB of
#   experts resident, inflating the on-card weight share). Resident after
#   the full offload: 10.16 GiB of dense/attention/MTP/ViT/lm_head weights.
#   Matching is greedy-up-to-budget in traversal order; unmatched params are
#   never offloaded.
OFFLOAD_BACKEND=uva
OFFLOAD_GB=82
OFFLOAD_PARAMS=ple,experts

# --- engine -----------------------------------------------------------------
# No aiter wheel in this image (gfx9-only upstream); the AMD qwen4_exp path
# runs its in-tree triton kernels. Deterministic rather than relying on the
# availability probe.
VLLM_ROCM_USE_AITER=0
# Compile/inductor/triton caches (container /cache, TRITON_CACHE_DIR etc.)
CACHE_ROOT=/cache

# --- parsers / template (the harness wire contract) ---------------------------
# vLLM 0.30 emits the thinking channel as `reasoning` (the deprecated
# `reasoning_content` is renamed server-side, chat_completion/protocol.py:554).
# The qwen3 reasoning parser extracts the template's think-block tags into
# that channel; the qwen3_xml tool parser structures tool-call XML output into
# tool_calls (auto-tool-choice enables the structured path for API clients).
# The family precedent is the host's own Ornith-era serve scripts
# (~/vllm/failedAttempts/OrnithFP8.sh); the FP8 tokenizer's template
# consumes enable_thinking + preserve_thinking (verified in tokenizer_config).
TOOL_PARSER=qwen3_xml
REASONING_PARSER=qwen3
CHAT_TEMPLATE_KWARGS='{"enable_thinking": true, "preserve_thinking": true}'

# --- speculative decode ------------------------------------------------------
# The hybrid stack (GatedDeltaNet + QSA short-conv) uses the v1 engine's
# mamba-capable attention backends, negotiated by the model, not by env.
# MTP drafting comes from the model's own mtp.* weights via
# --speculative-config, only when SPEC_CONFIG is non-empty. Bring-up runs
# with it empty on purpose: measure the base shape clean, then A/B; never
# change two knobs at once.
SPEC_CONFIG=


# --- container ---------------------------------------------------------------
IMAGE=localhost/frank-primary:vllm030
CONTAINER_NAME=frank-primary-vllm