frank-small.Which one to pick? Screenshots and photos: frank-small.
diff --git a/shared/homepage/services.json b/shared/homepage/services.json
index dd91063..8810bd7 100644
--- a/shared/homepage/services.json
+++ b/shared/homepage/services.json
@@ -244,7 +244,7 @@
{
"name": "frank-medium",
"category": "user",
- "description": "The 27B generalist. ajgazin Swift-Qwen3.8-27B-Uncensored at UD-Q8_K_XL with its own MTP head, mainline llama.cpp in one 35:30 layer-split process across Dankserver's two R9700s, 393k-token context.",
+ "description": "The 27B generalist. Qwen3.8-27B-Uncensored at MXFP4 on vllm-radiance, one tensor-parallel process across Dankserver's two R9700s with a DFlash2 drafter; 262k-token context shared by up to eight conversations.",
"url": "",
"docs": "/docs#models",
"probe": "192.168.0.235:7770",
diff --git a/tests/changed_tests.bats b/tests/changed_tests.bats
index 49c8c08..19c730c 100644
--- a/tests/changed_tests.bats
+++ b/tests/changed_tests.bats
@@ -21,10 +21,18 @@ load helpers
[[ "$output" != *"tests/homepage_pages.bats"* ]]
}
-@test "changed-test wrapper maps the frank-medium trio to its focused tests" {
- run bash "$REPO_ROOT/scripts/test-changed.sh" --list --paths scripts/frank-medium.env
+@test "changed-test wrapper maps the frank-medium dir to its focused tests" {
+ run bash "$REPO_ROOT/scripts/test-changed.sh" --list --paths \
+ dankserver/frank-medium/quadlet/frank-medium.container
[ "$status" -eq 0 ]
[[ "$output" == *"tests/frank_medium_unit.bats"* ]]
[[ "$output" == *"tests/deployment_scoping.bats"* ]]
+ [[ "$output" == *"tests/docs_completeness.bats"* ]]
[[ "$output" != *"tests/homepage_pages.bats"* ]]
+ # The llama trio's old path must no longer select the container seam: the
+ # mapping was removed with the runtime, and a stale case here would keep
+ # firing tests for an archived service.
+ run bash "$REPO_ROOT/scripts/test-changed.sh" --list --paths scripts/frank-medium.env
+ [ "$status" -eq 0 ]
+ [[ "$output" != *"tests/frank_medium_unit.bats"* ]]
}
diff --git a/tests/deployment_scoping.bats b/tests/deployment_scoping.bats
index 35146af..30d0ee3 100644
--- a/tests/deployment_scoping.bats
+++ b/tests/deployment_scoping.bats
@@ -46,18 +46,25 @@ REMOTE_DEPLOY="$REPO_ROOT/scripts/deploy-remote.sh"
[ -z "$output" ]
}
-@test "deployment planner maps the frank-medium scripts trio to frank-medium only" {
+@test "deployment planner maps the frank-medium container dir to frank-medium only" {
run python3 "$PLANNER" --target dankserver --paths \
- scripts/frank-medium.env scripts/frank-medium.service scripts/serve-frank-medium.sh
+ dankserver/frank-medium/quadlet/frank-medium.container \
+ dankserver/frank-medium/radiance-entrypoint.sh \
+ dankserver/frank-medium/frank-medium-healthcheck.py
[ "$status" -eq 0 ]
[ "$output" = "frank-medium" ]
- # The path is not the assertion: with the vllm-radiance service dir
- # retired into the trash, a planner rule still naming dankserver/frank-medium
- # would plan nothing and look identical to a correct one. Assert the
- # invariant (the dir is gone) as well as the mapping above.
- [ ! -d "$REPO_ROOT/dankserver/frank-medium" ]
- run python3 "$PLANNER" --target dankserver --paths dankserver/frank-medium/quadlet/frank-medium-a.container
+ # The path is not the assertion: both retired shapes are still in the tree
+ # as archive, and a rule matching either would restart a service nobody
+ # runs. Assert the negatives explicitly, plus the llama trio's old paths,
+ # whose mapping was removed with the runtime.
+ run python3 "$PLANNER" --target dankserver --paths \
+ dankserver/.AGENTTRASH/20260916-vllm-radiance/frank-medium-a.container
+ [ "$status" -eq 0 ]
+ [ -z "$output" ]
+ run python3 "$PLANNER" --target dankserver --paths \
+ scripts/.AGENTTRASH/20260920-llama-layersplit/frank-medium.env.llamacpp-layersplit \
+ scripts/frank-medium.env
[ "$status" -eq 0 ]
[ -z "$output" ]
}
diff --git a/tests/frank_medium_unit.bats b/tests/frank_medium_unit.bats
index a41939a..8a099b8 100755
--- a/tests/frank_medium_unit.bats
+++ b/tests/frank_medium_unit.bats
@@ -1,351 +1,193 @@
#!/usr/bin/env bats
-# Seam: the frank-medium mainline-llama.cpp root unit on dankserver.
-# frank-medium became a native llama.cpp service on 2026-09-16, replacing the
-# vllm-radiance replica pair + routing proxy that served this endpoint for a
-# day. What this seam pins is what the flags alone do not say: boot persistence
-# for a NATIVE runtime (no generated quadlet is involved), that BOTH cards work
-# on ONE model through a layer split with no collective in the path, that the
-# DFlash2 drafter is wired with a depth its block size actually allows, that the
-# runtime and payload are pinned rather than floated, and that one slot's KV
-# still fits a 32 GiB card beside the weights it holds.
+# Seam: the frank-medium vllm-radiance container on dankserver.
+# frank-medium became a CONTAINER again on 2026-09-20, when the board swap put
+# both R9700s on CPU root ports and a measured three-arm comparison retired the
+# mainline-llama.cpp layer split (scripts/.AGENTTRASH/20260920-llama-layersplit/).
+# What this seam pins is what the flags alone do not say: boot persistence for a
+# GENERATED unit (this host's v1 quadlet generator cannot enable units, so the
+# [Install] section is the only thing that survives a reboot), that BOTH cards
+# work on ONE model through tensor parallelism — the thing the pre-2026-09-20
+# hardware could not do — the KV pin's coupling to the batch shape it was
+# calibrated at, and that the pool still holds one full-window request.
load helpers
-UNIT="$REPO_ROOT/scripts/frank-medium.service"
-SERVE="$REPO_ROOT/scripts/serve-frank-medium.sh"
-ENV_FILE="$REPO_ROOT/scripts/frank-medium.env"
-BUILD="$REPO_ROOT/scripts/build-llama-rdna4.sh"
-FETCH="$REPO_ROOT/scripts/download-frank-medium-gguf.sh"
+UNIT="$REPO_ROOT/dankserver/frank-medium/quadlet/frank-medium.container"
+ENTRY="$REPO_ROOT/dankserver/frank-medium/radiance-entrypoint.sh"
+HEALTH="$REPO_ROOT/dankserver/frank-medium/frank-medium-healthcheck.py"
REMOTE_DEPLOY="$REPO_ROOT/scripts/deploy-remote.sh"
+LLAMA_TRASH="$REPO_ROOT/scripts/.AGENTTRASH/20260920-llama-layersplit"
+REPLICA_TRASH="$REPO_ROOT/dankserver/.AGENTTRASH/20260916-vllm-radiance"
-# Measured constants (rocm-smi / HF blob sizes), used by the fit arithmetic.
-CARD_BYTES=34208743424 # one R9700 as rocm-smi reports it
-MODEL_BYTES=29047084416 # orcarouter Q8_0 target
-DRAFT_BYTES=1143006816 # DFlash2 Q4_K_M drafter
-
-@test "frank-medium's unit, serve script, env and its build/fetch scripts exist" {
- [ -f "$UNIT" ]
- [ -f "$SERVE" ]
- [ -f "$ENV_FILE" ]
- [ -f "$BUILD" ]
- [ -f "$FETCH" ]
+# Measured constants, used by the fit arithmetic.
+CARD_BYTES=34208743424 # one R9700 as rocm-smi reports it (32624 MiB)
+KV_BYTES_PER_TOKEN=70656 # --kv-cache-memory 18563072000 => "262,720 tokens"
+env_value() {
+ sed -nE "s/^Environment=$1=(-?[0-9]+)$/\1/p" "$UNIT" | head -n1
+}
+# GPU_UTIL is a fraction, not a count; the integer reader would drop it.
+env_ratio() {
+ sed -nE "s/^Environment=$1=([0-9.]+)$/\1/p" "$UNIT" | head -n1
}
-@test "frank-medium is boot-persistent, self-healing and unprivileged" {
- grep -q '^WantedBy=multi-user.target$' "$UNIT"
+@test "frank-medium's unit, entrypoint and healthcheck exist" {
+ [ -f "$UNIT" ]
+ [ -x "$ENTRY" ]
+ [ -f "$HEALTH" ]
+}
+
+@test "frank-medium is boot-persistent and self-healing" {
+ # Generated units cannot be enabled on this host, so WantedBy in the file is
+ # the whole boot story (AGENTS.md: Boot Persistence & Self-Healing).
+ grep -q '^WantedBy=default.target$' "$UNIT"
grep -q '^Restart=on-failure$' "$UNIT"
grep -q '^RestartSec=' "$UNIT"
- grep -q '^User=dank$' "$UNIT"
- grep -q '^LimitMEMLOCK=infinity$' "$UNIT"
+ # First start compiles Triton/inductor kernels before the engine loads ~9.5
+ # GiB per card; a shorter timeout kills a healthy boot.
+ grep -q '^TimeoutStartSec=1800$' "$UNIT"
+ grep -q '^HealthCmd=python3 /usr/local/bin/frank-medium-healthcheck.py$' "$UNIT"
+ grep -q '^HealthStartPeriod=1800s$' "$UNIT"
+ # Boots must not depend on the registry.
+ grep -q '^Pull=never$' "$UNIT"
}
-@test "frank-medium runs the repo's own serve script with the repo's env" {
- grep -q '^ExecStart=/home/dank/serverAppConfigs/scripts/serve-frank-medium.sh$' "$UNIT"
- grep -q 'FRANK_MEDIUM_ENV_FILE=/home/dank/serverAppConfigs/scripts/frank-medium.env' "$UNIT"
+@test "both R9700s serve ONE model as one tensor-parallel process" {
+ grep -q '^Environment=TP=2$' "$UNIT"
+ grep -q '^Environment=ROCR_VISIBLE_DEVICES=0,1$' "$UNIT"
+ grep -q '^Environment=HIP_VISIBLE_DEVICES=0,1$' "$UNIT"
+ grep -q -- '--tensor-parallel-size "$TP"' "$ENTRY"
+ # The iGPU (index 2, 2 GiB) must stay out of the visible set: a third rank
+ # would take layers onto system RAM.
+ ! grep -q '^Environment=.*VISIBLE_DEVICES=0,1,2' "$UNIT"
+ # TP needs the all-reduce to actually run. R4D is the collective-free path
+ # this host measured; the entrypoint must still select it, and the RCCL
+ # fallback must not be re-disabled by the pre-board-swap workarounds.
+ grep -q 'RADIANCE_USE_R4D_AR' "$ENTRY"
+ grep -q -- '--attention-backend "$ATTN"' "$ENTRY"
+ ! grep -q 'NCCL_P2P_DISABLE' "$UNIT"
+ ! grep -q 'RCCL_MSCCL_ENABLE' "$UNIT"
}
-@test "both R9700s serve ONE model, layer-split inside one process" {
- grep -q '^SPLIT_MODE=layer$' "$ENV_FILE"
- grep -q '^DEVICES=ROCm0,ROCm1$' "$ENV_FILE"
- # The split is a layer PAIR: the shares add up to the model's 65 blocks (one
- # -ts unit per layer). The operator asked for the tensors BALANCED across
- # the two cards (2026-09-19), which for 65 layers is 32:33 -- the most even
- # split that exists, with ROCm1 (the last-layers card, which also carries
- # the drafter and the output layers) holding the extra one. WHICH pair
- # balances the cards is the fit test's job, which recomputes it from this
- # file; pinning a literal here would only mean that re-measuring the
- # balance breaks a test about parallelism.
- local split_hi split_lo
- split_hi="$(sed -nE 's/^TENSOR_SPLIT=([0-9]+),([0-9]+)$/\1/p' "$ENV_FILE")"
- split_lo="$(sed -nE 's/^TENSOR_SPLIT=([0-9]+),([0-9]+)$/\2/p' "$ENV_FILE")"
- [ -n "$split_hi" ] && [ -n "$split_lo" ]
- [ $(( split_hi + split_lo )) -eq 65 ]
- [ $(( split_lo - split_hi )) -le 1 ]
- grep -q -- '--split-mode "$SPLIT_MODE"' "$SERVE"
- grep -q -- '--device "$DEVICES"' "$SERVE"
- grep -q -- '--tensor-split "$TENSOR_SPLIT"' "$SERVE"
- # Tensor split is the one shape this host cannot run: it needs a cross-card
- # collective, and the second card cannot dispatch one (see the env file).
- ! grep -q '^SPLIT_MODE=tensor$' "$ENV_FILE"
+@test "HIP never reads one of these tunables as its own setting" {
+ # HIP reads bare TEMP, HOST and GPU_MAX_HEAP_SIZE (2026-08-13 incident:
+ # TEMP=1.0 sent the JIT cache to path "1.0" and segfaulted every load).
+ # Serve scripts export env files with `set -a`; a container inherits the
+ # same hazard from Environment=.
+ ! grep -qE '^Environment=(TEMP|HOST|GPU_MAX_HEAP_SIZE)=' "$UNIT"
}
-@test "the iGPU is hidden so no layer can land on system RAM" {
- grep -q '^HIP_VISIBLE_DEVICES=0,1$' "$ENV_FILE"
- grep -q '^export HIP_VISIBLE_DEVICES$' "$SERVE"
+@test "the drafter is DFlash2 at the measured depth and the kernel band covers the batch" {
+ grep -q '^Environment=SPEC_METHOD=dflash$' "$UNIT"
+ local maxseqs spec chunk
+ spec="$(env_value SPEC)"
+ maxseqs="$(env_value MAXSEQS)"
+ chunk="$(env_value CHUNK)"
+ [ -n "$spec" ] && [ -n "$maxseqs" ] && [ -n "$chunk" ]
+ # DFlash2 drafts at most 7 tokens per step; deeper is a different drafter's
+ # contract and costs acceptance, not just VRAM.
+ [ "$spec" -eq 7 ]
+ # The MXFP4 decode kernel band covers MAXSEQS x (SPEC+1) rows, and the
+ # shipped default covers 64. Exceeding it without the entrypoint's >8 bump
+ # is a launch failure at the worst moment (first concurrent request).
+ [ $(( maxseqs * (spec + 1) )) -le 64 ]
+ grep -q 'RADIANCE_MXFP4_DECODE_MAX_M' "$ENTRY"
+ # The chunk is the AR size gate's input (CHUNK x hidden x 2 bytes); a chunk
+ # larger than this row's silently changes which all-reduce path runs.
+ [ "$chunk" -le 8192 ]
}
-@test "the drafter is the DFlash2 sidecar at the measured depth" {
- # The DFlash2 sidecar is the deployed drafter (operator call 2026-09-19).
- # n_max 7 is the measured DFlash2 winner -- 43.5 tok/s at 41 % acceptance
- # against 32.4 for the in-file MTP head at n=3 (the env's table; identical
- # greedy text at every depth, so this is pure speed). The target file
- # also carries its own MTP head (nextn_predict_layers=1), so draft-mtp is
- # one SPEC_TYPE change away; the drafter file stays on disk for that.
- grep -qE '^SPEC_TYPE=draft-dflash$' "$ENV_FILE"
- grep -q -- '--spec-type "$SPEC_TYPE"' "$SERVE"
- local n_max
- n_max="$(sed -nE 's/^SPEC_DRAFT_N_MAX=([0-9]+)$/\1/p' "$ENV_FILE")"
- [ -n "$n_max" ] && [ "$n_max" -eq 7 ]
- # The Q4_K_M rung is the operator's requested drafter quant -- the
- # drafter's job is throughput, not output quality, and the target
- # verifies every drafted token. ngram-mod's window is retained in the env
- # for the chain, so it may not be dropped.
- grep -q '^DRAFT_MODEL_FILE=Qwen3\.8-27B-DFlash2-Q4_K_M\.gguf$' "$ENV_FILE"
- grep -q '^SPEC_NGRAM_N_MATCH=24$' "$ENV_FILE"
- # ...and neither is loaded: ngram-mod's flags only go out when the type
- # contains ngram, so a pure dflash configuration is not handed them.
- python3 -c "
-lines = open('$SERVE').read().splitlines()
-guard = next(i for i, l in enumerate(lines) if '*ngram*' in l)
-indent = len(lines[guard]) - len(lines[guard].lstrip())
-end = next(i for i in range(guard + 1, len(lines))
- if lines[i].strip() == 'fi' and len(lines[i]) - len(lines[i].lstrip()) == indent)
-assert '--spec-ngram-mod-n-match' in chr(10).join(lines[guard:end]), 'ngram flags must sit in the ngram branch'
-"
+@test "the KV pin is valid only at the shape it was calibrated for" {
+ # The pin is the upstream kv-profiles.tsv row for sig 2x7551-32624 at
+ # maxseqs=8 chunk=8192 maxlen=262144 spec=dflash — exactly this host. It is
+ # not a general-purpose budget: changing MAXSEQS, CHUNK or SPEC_METHOD
+ # invalidates it, so the shape has to move with it or the pin goes to 0
+ # (let the image profile the shape).
+ local kv_mem maxseqs chunk maxlen spec
+ kv_mem="$(env_value KV_MEM)"
+ maxseqs="$(env_value MAXSEQS)"
+ chunk="$(env_value CHUNK)"
+ maxlen="$(env_value MAXLEN)"
+ spec="$(env_value SPEC)"
+ [ -n "$kv_mem" ] && [ -n "$maxseqs" ] && [ -n "$chunk" ] && [ -n "$maxlen" ]
+ grep -q 'kv-profiles.tsv' "$UNIT"
+ [ "$maxseqs" -eq 8 ] && [ "$chunk" -eq 8192 ] && [ "$spec" -eq 7 ]
+ grep -q '^Environment=SPEC_METHOD=dflash$' "$UNIT"
+ # Pool arithmetic, from the engine's own boot line: 18563072000 bytes
+ # reserved => "GPU KV cache size: 262,720 tokens". The pool must hold at
+ # least ONE full-window request or the endpoint refuses its own
+ # --max-model-len, and it must fit on one card beside the weights.
+ [ $(( kv_mem / KV_BYTES_PER_TOKEN )) -ge "$maxlen" ]
+ # 9.5 GiB of MXFP4 weights per card + the KV pool, under the 0.98 util cap.
+ local weights=10200547328 # ~9.5 GiB per card of the 19 GB MXFP4 checkpoint
+ local util util_pct floor
+ util="$(env_ratio GPU_UTIL)"
+ [ -n "$util" ]
+ util_pct="${util#0.}"
+ floor=$(( 1024 * 1024 * 1024 )) # 1 GiB per card
+ [ $(( weights + kv_mem / 2 )) -le $(( CARD_BYTES * util_pct / 100 - floor )) ]
}
-@test "a draft MODEL is passed only for DFlash types, never for MTP" {
- # MTP builds its context against the TARGET model (its head lives in that
- # GGUF). Passing --spec-draft-model alongside it points the draft context at
- # the drafter's file, which has no MTP layers, and the server dies at load:
- # context type MTP requested but model doesn't contain MTP layers
- # failed to create MTP context
- # So the flag must appear exactly once, inside the dflash branch.
- python3 -c "
-lines = open('$SERVE').read().splitlines()
-guard = next(i for i, l in enumerate(lines) if '*dflash*' in l)
-indent = len(lines[guard]) - len(lines[guard].lstrip())
-end = next(i for i in range(guard + 1, len(lines))
- if lines[i].strip() == 'fi' and len(lines[i]) - len(lines[i].lstrip()) == indent)
-block = chr(10).join(lines[guard:end])
-assert '--spec-draft-model' in block, 'the dflash branch must pass the draft model'
-assert sum(l.count('--spec-draft-model') for l in lines) == 1, 'only that branch may pass it'
-print('draft-model wiring ok')
-"
+@test "the fleet endpoint contract survives the runtime swap" {
+ grep -q '^Environment=PORT=7770$' "$UNIT"
+ grep -q '^Environment=SERVED_NAMES=frank-medium$' "$UNIT"
+ grep -q -- '--port "$PORT"' "$ENTRY"
+ grep -q -- '--served-model-name $SERVED_NAMES' "$ENTRY"
+ # Host network: vLLM binds the port itself, so no PublishPort (and no
+ # pasta bind, which is what made the retired proxy's port replacement
+ # fail at container create).
+ grep -q -- '--network=host' "$UNIT"
+ ! grep -q '^PublishPort=' "$UNIT"
+ # Tools and reasoning are part of the harness contract; both parsers must
+ # be selected, and thinking must land in its own field.
+ grep -q -- '--enable-auto-tool-choice' "$ENTRY"
+ grep -q -- '--tool-call-parser qwen3_coder' "$ENTRY"
+ grep -q -- '--reasoning-parser qwen3' "$ENTRY"
+ grep -q -- '--enable-prefix-caching' "$ENTRY"
+ # Requests that send no sampler fields get the predecessor's defaults.
+ grep -q '"temperature":0.7' "$ENTRY"
+ grep -q '"top_p":0.95' "$ENTRY"
}
-@test "the runtime is pinned to a commit and to gfx1201 alone" {
- # A floating ref would silently move the service between engine versions,
- # and an unpinned arch would build for a sibling GPU that loads and then
- # segfaults on these cards.
- grep -Eq '^LLAMA_REF="\$\{LLAMA_REF:-[0-9a-f]{40}\}"$' "$BUILD"
- grep -Eq '^HIP_ARCH="\$\{HIP_ARCH:-gfx1201\}"$' "$BUILD"
- grep -q 'GGML_HIP=ON' "$BUILD"
- grep -q 'frank-medium.env' "$SERVE"
+@test "the healthcheck proves the engine serves, not merely that a process lives" {
+ grep -q '"/health"' "$HEALTH" || grep -q '/health' "$HEALTH"
+ grep -q 'status == 200' "$HEALTH"
+ # PORT-aware, and it must not hard-code a replica port.
+ grep -q 'os.environ.get("PORT"' "$HEALTH"
+ ! grep -qE '7771|7772' "$HEALTH"
}
-@test "the payload is fetched resumably and verified by size and sha256" {
- grep -q 'Qwen3\.8-27B-Uncensored-Q8_0\.gguf' "$FETCH"
- grep -q 'Qwen3\.8-27B-DFlash2-Q4_K_M\.gguf' "$FETCH"
- grep -q -- '-fL -C -' "$FETCH"
- grep -q 'verifying sizes and sha256' "$FETCH"
- # The target repo is gated: the script must fail loud without a token
- # rather than write a 401 body to disk and report success.
- grep -q 'no HF token is available' "$FETCH"
-}
-
-@test "both cards stay balanced and keep the operator's 1.5 GiB floor" {
- local ctx parallel cache_k cache_v split_hi split_lo batch ubatch
- ctx="$(sed -nE 's/^CTX_SIZE=([0-9]+)$/\1/p' "$ENV_FILE")"
- parallel="$(sed -nE 's/^PARALLEL=([0-9]+)$/\1/p' "$ENV_FILE")"
- cache_k="$(sed -nE 's/^CACHE_TYPE_K=(.+)$/\1/p' "$ENV_FILE")"
- cache_v="$(sed -nE 's/^CACHE_TYPE_V=(.+)$/\1/p' "$ENV_FILE")"
- split_hi="$(sed -nE 's/^TENSOR_SPLIT=([0-9]+),([0-9]+)$/\1/p' "$ENV_FILE")"
- split_lo="$(sed -nE 's/^TENSOR_SPLIT=([0-9]+),([0-9]+)$/\2/p' "$ENV_FILE")"
- batch="$(sed -nE 's/^BATCH_SIZE=([0-9]+)$/\1/p' "$ENV_FILE")"
- ubatch="$(sed -nE 's/^UBATCH_SIZE=([0-9]+)$/\1/p' "$ENV_FILE")"
- spec_type="$(sed -nE 's/^SPEC_TYPE=(.+)$/\1/p' "$ENV_FILE")"
- [ -n "$ctx" ] && [ -n "$parallel" ] && [ -n "$cache_k" ] && [ -n "$cache_v" ] && [ -n "$spec_type" ]
- [ -n "$split_hi" ] && [ -n "$split_lo" ] && [ -n "$batch" ] && [ -n "$ubatch" ]
- [ "$parallel" -ge 1 ]
- [ "$batch" -ge "$ubatch" ]
- [ "$cache_k" = "f16" ] && [ "$cache_v" = "f16" ]
- # Per card, calibrated against rocm-smi at the 35:30 / ctx 262144 / batch
- # 6144 x ubatch 512 / two slots / DFlash2 point, where the two cards
- # measured 6.44 / 6.90 GiB free. The fit reproduces card 1 to 0.00 GiB
- # and card 0 to 0.86 GiB at that point; it is a GATE, not a meter -- the
- # deployed point is re-measured on the host after every split/ctx/batch
- # move (the current one is 32:33 / 327680 / DFlash2 Q4_K_M, the balanced
- # split the operator asked for on 2026-09-19 -- see the TENSOR_SPLIT
- # header in frank-medium.env).
- #
- # card 0 = its share of the weights and of the KV (qwen35 spends KV on
- # its 16 full-attention layers only: 2 (K,V) x 4 heads x 256 dim
- # x 2 B = 64 KiB per token at f16) plus ~1.4e6 B per ubatch unit
- # of compute buffers
- # card 1 = the same for its own share, plus the drafter. The drafter's
- # charge depends on WHAT it is: DFlash2 is a sidecar file, so
- # its weights (2.06e9 B) plus window-bounded KV (20480 B/pos x
- # 2048) plus ~0.89 GiB of constant buffers; MTP's head lives in
- # the target file (already charged above), so its cost is one
- # nextn layer's KV (4096 B/position) plus small buffers. Its
- # compute buffers are the heavier ones either way, because it
- # holds the output layers and the drafter's graphs.
- #
- # BOTH ubatch coefficients are measured at the deployed shape, from the
- # 1536 -> 512 move: 1.30 GiB on card 0 and 2.41 GiB on card 1. That
- # asymmetry is why shrinking the batch moved the balance toward card 1 and
- # cost card 0 a layer -- the split and the batch cannot be chosen apart.
- #
- # The layer it charges for is the AVERAGE (0.70 GiB: 31.46e9 of weights plus
- # 16 GiB of KV over 65 layers). This stack is a hybrid, so real steps vary
- # around that -- 0.43 GiB for a DeltaNet layer, 1.43 GiB for a full-attention
- # one -- which makes the drift check below CONSERVATIVE: it overstates the gap
- # a one-layer move creates, and so trips on moves a measurement might bless.
- # That is the intent: moving the split means re-measuring, not re-arguing.
- #
- # The slack is the DEPLOYED gap, rounded up: at each shape the balance
- # cannot be tuned finer than one layer, so the deployed split's gap IS
- # what the check must accept, and a tighter slack would only reject it.
- #
- # What this model cannot see is CONTIGUITY -- the mechanism by which the
- # DSpark-era 8192/2048 failed, a 2020 MiB pp buffer that found no room while
- # every total looked fine. Total bytes are not the whole story for one big
- # allocation.
- local kv_pos=65536 draft_kv_pos=20480 mtp_kv_pos=4096 floor slack
- local card_hi card_lo diff
- local mmproj=931145984 # mmproj-Qwen3.8-27B-Uncensored-f16.gguf, on the primary device
- # 1.5 GiB was the floor until the 2x196k shape: the 34:31 / 393216 /
- # MTP point measured 28.91 / 30.78 GiB, leaving 2.95 / 1.08 GiB, so the
- # floor is the measured 1.08 GiB rounded down. The 32:33 / 327680 /
- # DFlash2 point is roomier than that (fit: 6.97 / 4.89 GiB free), so the
- # floor stays at the measured 1.0 GiB -- if a large allocation fails at
- # load, the next lever is a ctx cut, not a floor change.
- floor=$(( 1024 * 1024 * 1024 )) # 1.0 GiB per card
- # The deployed point (32:33 at ctx 327680 with DFlash2) has a fit gap of
- # 2082 MiB -- the balanced split the operator asked for, not the
- # tightest reachable one. The slack sits at 2150 MiB: it accepts the
- # deployed split and rejects a two-layer re-skew (34:31 / 31:34 both
- # move the fit gap well past it). The x16-lean 35:30 that served the
- # predecessor payload (gap 0.58 GiB) no longer applies: the operator
- # chose symmetry over the x1-card bottleneck.
- slack=$(( 2150 * 1024 * 1024 ))
- card_hi=$(( MODEL_BYTES * split_hi / (split_hi + split_lo) \
- + kv_pos * ctx * split_hi / (split_hi + split_lo) \
- + 381898377 \
- + mmproj \
- + 1363 * 1024 * ubatch ))
- if [[ "$spec_type" == *dflash* || "$spec_type" == *dspark* ]]; then
- card_lo=$(( MODEL_BYTES * split_lo / (split_hi + split_lo) \
- + DRAFT_BYTES \
- + kv_pos * ctx * split_lo / (split_hi + split_lo) \
- + draft_kv_pos * (ctx < 2048 ? ctx : 2048) \
- + 955046413 \
- + 2468 * 1024 * ubatch ))
- else
- # MTP: the head is in the target file (charged above); one nextn
- # layer's KV plus buffers/graphs. The constant is CALIBRATED to the
- # deployed point (2026-09-17, 34:31 / 393216): card 1 measured 30.78
- # GiB, of which 4.20 GiB is MTP's total charge -- 1.61 GiB of nextn KV
- # plus 2.70 GiB of buffers and graphs, far more than the 0.2 GiB
- # estimate the DFlash2-era shape suggested.
- card_lo=$(( MODEL_BYTES * split_lo / (split_hi + split_lo) \
- + kv_pos * ctx * split_lo / (split_hi + split_lo) \
- + mtp_kv_pos * ctx \
- + 2901231913 \
- + 2468 * 1024 * ubatch ))
- fi
- [ "$card_hi" -le $(( CARD_BYTES - floor )) ]
- [ "$card_lo" -le $(( CARD_BYTES - floor )) ]
- diff=$(( card_hi - card_lo )); [ "$diff" -ge 0 ] || diff=$(( -diff ))
- [ "$diff" -le "$slack" ]
- # ...and the window may not wander far past what the checkpoint was
- # trained for (262144; the GGUF carries no rope scaling, so positions
- # past that extrapolate on the base rope). The deployed 327680 pool is
- # two 163840 slots -- entirely trained territory.
- [ "$ctx" -le 393216 ]
-}
-
-@test "the host-RAM prompt cache can hold a full slot's state" {
- # --cache-ram is the one cache tunable that is NOT VRAM: it caps the total
- # bytes of saved prompt states in host RAM (server_prompt_cache, in
- # tools/server/server-task.cpp). alloc() REFUSES any single state larger
- # than the whole cap -- silently, with one WRN line -- so a budget below
- # one slot's full context makes every deep conversation uncacheable and
- # every turn past it re-prefill from scratch. That was the deployed state
- # on 2026-09-18: 137 refusals of 11.0-11.4 GiB states against the 8192 MiB
- # cap, in two days of journal.
- #
- # The state law at this shape, per token of sequence: 16 full-attention
- # layers x 4 kv heads x 256 dim x 2 B x 2 (K,V) = 64 KiB, plus 4096 B for
- # the MTP draft context's own KV. The DeltaNet state is constant-size and
- # is left out of the sum -- which only makes this gate more conservative.
- local ctx parallel cache_mib per_token slot_state host_mib
- ctx="$(sed -nE 's/^CTX_SIZE=([0-9]+)$/\1/p' "$ENV_FILE")"
- parallel="$(sed -nE 's/^PARALLEL=([0-9]+)$/\1/p' "$ENV_FILE")"
- cache_mib="$(sed -nE 's/^CACHE_RAM=([0-9]+)$/\1/p' "$ENV_FILE")"
- [ -n "$ctx" ] && [ -n "$parallel" ] && [ -n "$cache_mib" ]
- per_token=$(( (16 * 4 * 256 * 2 * 2) + (4 * 256 * 2 * 2) ))
- slot_state=$(( per_token * (ctx / parallel) ))
- # one full slot must fit, or the cache is decorative
- [ "$cache_mib" -ge $(( slot_state / 1024 / 1024 )) ]
- # ...and this budget is host RAM: never more than half of dankserver's
- # 62220 MiB, which the media-stack co-tenants and the page cache share.
- host_mib=62220
- [ "$cache_mib" -le $(( host_mib / 2 )) ]
- # the arithmetic above is about nothing unless the flag goes out
- grep -q -- '--cache-ram "$CACHE_RAM"' "$SERVE"
- grep -q -- '--cache-prompt' "$SERVE"
-}
-
-@test "vision is enabled: the f16 projector loads with the model" {
- grep -q '^NO_MMPROJ=0$' "$ENV_FILE"
- grep -q '^MM_PROJ_FILE=mmproj-Qwen3\.8-27B-Uncensored-f16\.gguf$' "$ENV_FILE"
- # Explicit flag, not autoload: this build starts text-only without it,
- # and refuses to start without the projector file, so a missing file is
- # a deploy error, not a silent text-only server.
- grep -q -- '--mmproj "$MM_PROJ"' "$SERVE"
- grep -q 'vision is enabled but the projector is missing' "$SERVE"
- # And the download script fetches and byte-verifies it.
- grep -q '^MM_PROJ_SIZE=931145984$' "$FETCH"
- grep -q -- 'check "$MODEL_DIR/$MM_PROJ_FILE" "$MM_PROJ_SIZE"' "$FETCH"
-}
-
-@test "the fleet endpoint and the predecessor's sampler defaults survive" {
- grep -q '^ALIAS=frank-medium$' "$ENV_FILE"
- grep -q '^LISTEN_PORT=7770$' "$ENV_FILE"
- grep -q -- '--alias "$ALIAS"' "$SERVE"
- grep -q -- '--port "$LISTEN_PORT"' "$SERVE"
- grep -q -- '--host "$BIND_ADDR"' "$SERVE"
- # Prometheus scrapes this endpoint for LLM fleet metrics.
- grep -q -- '--metrics' "$SERVE"
- # Requests that send no sampler fields get these instead of an error.
- grep -q '^TEMPERATURE=0.7$' "$ENV_FILE"
- grep -q '^TOP_P=0.95$' "$ENV_FILE"
-}
-
-@test "the deploy handler installs the root unit and refuses a missing payload" {
+@test "the deploy handler gates on host assets and installs the quadlet" {
grep -q 'deploy_llm_medium' "$REMOTE_DEPLOY"
- grep -q 'relink_unit frank-medium' "$REMOTE_DEPLOY"
- grep -q 'systemctl enable frank-medium.service' "$REMOTE_DEPLOY"
- grep -q 'systemctl restart frank-medium.service' "$REMOTE_DEPLOY"
- grep -q '127.0.0.1:7770/health' "$REMOTE_DEPLOY"
- grep -q 'build-llama-rdna4.sh' "$REMOTE_DEPLOY"
- grep -q 'download-frank-medium-gguf.sh' "$REMOTE_DEPLOY"
- grep -q '\[\[ "$missing" -eq 0 \]\] || return 1' "$REMOTE_DEPLOY"
-}
-
-@test "the deploy handler retires the vLLM quadlets and frees the port they held" {
- grep -q 'retire_vllm_medium_quadlets' "$REMOTE_DEPLOY"
- grep -q 'systemctl --user stop frank-medium-a.service frank-medium-b.service' "$REMOTE_DEPLOY"
+ grep -q 'install_quadlet frank-medium dankserver/frank-medium/quadlet frank-medium' "$REMOTE_DEPLOY"
+ grep -q 'wait_container_healthy frank-medium' "$REMOTE_DEPLOY"
grep -q 'wait_port_free 7770' "$REMOTE_DEPLOY"
- # No image left to tag: the runtime is a native binary now.
- # ...and no image work or quadlet install of the predecessor survives.
+ grep -q '\[\[ "$missing" -eq 0 \]\] || return 1' "$REMOTE_DEPLOY"
+ # The image is only pulled when absent, and re-tagged to the name the unit
+ # actually runs (the quadlet path cannot resolve registry refs at create).
+ grep -q 'podman image exists "$LLM_MEDIUM_IMAGE_LOCAL"' "$REMOTE_DEPLOY"
+ grep -q 'podman tag "$LLM_MEDIUM_IMAGE" "$LLM_MEDIUM_IMAGE_LOCAL"' "$REMOTE_DEPLOY"
+ # The patched libr4d is not optional (the image's own build NaNs this model).
+ grep -q 'patched libr4d absent' "$REMOTE_DEPLOY"
+}
+
+@test "a generated unit is never asked to enable, and the llama unit is gone" {
+ # podman 5.x v1 generator: generated units cannot be enabled; asking makes
+ # the deploy fail on a unit that is already boot-persistent via [Install].
+ ! grep -q 'systemctl --user enable frank-medium' "$REMOTE_DEPLOY"
+ # ...and the root llama unit must be retired, not relinked: relinking would
+ # resurrect a service whose repo file no longer exists.
+ ! grep -q 'relink_unit frank-medium' "$REMOTE_DEPLOY"
+ grep -q 'retire_llama_medium_unit' "$REMOTE_DEPLOY"
+}
+
+@test "the llama layer split and the replica trio are archived, not deleted" {
+ [ -f "$LLAMA_TRASH/frank-medium.service.llamacpp-layersplit" ]
+ [ -f "$LLAMA_TRASH/frank-medium.env.llamacpp-layersplit" ]
+ [ -f "$LLAMA_TRASH/serve-frank-medium.sh.llamacpp-layersplit" ]
+ [ ! -f "$REPO_ROOT/scripts/frank-medium.env" ]
+ [ -f "$REPLICA_TRASH/frank-medium-a.container" ]
+ [ -f "$REPLICA_TRASH/frank-medium-proxy.container" ]
+ # The replicas stay retired: the handler stops them but never installs them.
+ grep -q 'systemctl --user stop frank-medium-a.service frank-medium-b.service' "$REMOTE_DEPLOY"
! grep -q 'install_quadlet frank-medium-a' "$REMOTE_DEPLOY"
- ! grep -q 'podman tag docker.io/stilldeadcode' "$REMOTE_DEPLOY"
-}
-
-@test "the retired vLLM deployment is gone from the repo, not merely unmapped" {
- [ ! -d "$REPO_ROOT/dankserver/frank-medium" ]
- [ ! -f "$REPO_ROOT/tests/frank_medium_quadlet.bats" ]
- # ...and the archive is present, so the two assertions above cannot pass
- # because a path went missing rather than because it stayed missing.
- [ -f "$REPO_ROOT/dankserver/.AGENTTRASH/20260916-vllm-radiance/frank-medium-a.container" ]
- [ -f "$REPO_ROOT/dankserver/.AGENTTRASH/20260916-vllm-radiance/radiance-entrypoint.sh" ]
-}
-
-@test "the serve script refuses to start on an incomplete host" {
- grep -q 'frank-medium: missing\|missing executable runtime\|missing or unreadable' "$SERVE"
- grep -q 'missing or unreadable target model' "$SERVE"
- grep -q 'missing or unreadable draft model' "$SERVE"
}