frank-primary: R9V radiance cutover wiring (launcher-driven serve + state gates)
Replace the vLLM 0.30 UVA-offload wiring (never deployed; llama.cpp b11030 endpoint replaced by Frank's order, downtime window open) with the R9V radiance-vLLM shape on the same root unit: - serve-frank-primary.sh: layer the on-host qualified setup state (104 tuned R9V_* keys, /home/dank/r9v-state/uncensored/setup.json) under repo production overrides, then exec the fork's own launcher through the docker->podman shim and block on docker wait so a crashed engine is a nonzero ExecStart (launch.sh --detach alone would fake green). Gates: pinned image by OCI manifest digest in RepoDigests, PLE at pinned byte count (stat -c %s), all GGUF shards + mmproj. - frank-primary.env: thin production overrides only (LAN bind 0.0.0.0, :7770, alias frank-primary, container frank-primary-r9v, GPU BDFs); tuned engine shape stays in the setup state by design. - frank-primary.service: same root-unit shape (User=dank, LimitMEMLOCK=infinity for the tiered-expert pin), plus ExecStop podman stop — docker wait cannot stop the container child. - deploy-remote.sh deploy_llm_primary: state-driven gates (state ready, image digest present in rootless storage, PLE bytes, shard files) replace the fp030 shard-index gate; false-green MainPID check kept. - tests/frank_primary_unit.bats: seam rewritten for the R9V shape.
This commit is contained in:
Frank
+55
-26
@@ -1183,42 +1183,70 @@ deploy_llm_small() {
|
||||
wait_for_health frank-small http://127.0.0.1:7771/health 900
|
||||
}
|
||||
|
||||
# deploy_llm_primary — frank-primary is vLLM 0.30 (locally built ROCm image,
|
||||
# gfx1201) serving Qwen3.8-Flash-Next-FP8 on the two R9700s as a ROOT unit
|
||||
# whose serve script execs a rootless-podman container as dank. Same port and
|
||||
# alias as the llama.cpp endpoint it replaces (2026-09-27 cutover); the
|
||||
# harness models.yml and homepage cards are unchanged.
|
||||
# deploy_llm_primary — frank-primary is the R9V radiance-vLLM fork (docker-
|
||||
# pinned prebuilt, gfx1201, driven through the docker->podman shim) serving
|
||||
# Qwen3.8-Flash-Next-Uncensored IQ4_XS with the MTP4 drafter on the two
|
||||
# R9700s as a ROOT unit whose serve script execs the fork's launcher through
|
||||
# rootless podman as dank. Same port and alias as the llama.cpp endpoint it
|
||||
# replaced (2026-09-27 cutover); the harness models.yml id is unchanged.
|
||||
#
|
||||
# Gates: the image must exist in dank's rootless storage, and the payload
|
||||
# must be complete — every shard named by the model's own
|
||||
# model.safetensors.index.json present on disk (131 shards, 172.78 GiB;
|
||||
# per-shard sha256 + byte-count verification is download-frank-primary-fp8.sh's
|
||||
# job at fetch time, never re-hashed here).
|
||||
LLM_PRIMARY_IMAGE=localhost/frank-primary:vllm030
|
||||
LLM_PRIMARY_ROOT=/home/dank/models/Qwen3.8-Flash-Next-FP8
|
||||
LLM_PRIMARY_CONTAINER=frank-primary-vllm
|
||||
# Gates: the on-host R9V setup state must exist and be ready (it carries the
|
||||
# pinned image digest and every payload path), the pinned runtime image must
|
||||
# be loadable from dank's rootless storage by its OCI manifest digest, the
|
||||
# PLE payload must match its pinned byte count, and every GGUF shard + the
|
||||
# mmproj must exist (per-file sha256 verification was setup's job at fetch
|
||||
# time, never re-hashed here).
|
||||
LLM_PRIMARY_STATE=/home/dank/r9v-state/uncensored/setup.json
|
||||
LLM_PRIMARY_CONTAINER=frank-primary-r9v
|
||||
|
||||
deploy_llm_primary() {
|
||||
# Refuse rather than restart-loop: a unit whose image or payload is
|
||||
# missing never becomes healthy, and a green deploy would leave the
|
||||
# endpoint dark with nothing in the log to say why.
|
||||
if ! podman image inspect "$LLM_PRIMARY_IMAGE" >/dev/null 2>&1; then
|
||||
echo "ERROR: image absent: $LLM_PRIMARY_IMAGE" >&2
|
||||
echo "frank-primary: build the fp030 image first (see the runbook)" >&2
|
||||
if [[ ! -f "$LLM_PRIMARY_STATE" ]]; then
|
||||
echo "ERROR: R9V setup state absent: $LLM_PRIMARY_STATE" >&2
|
||||
echo "frank-primary: run the profile setup on this host first" >&2
|
||||
return 1
|
||||
fi
|
||||
local want_shards have_shards
|
||||
want_shards="$(python3 - "$LLM_PRIMARY_ROOT/model.safetensors.index.json" <<'PY'
|
||||
import json, sys
|
||||
print(len(set(json.load(open(sys.argv[1]))["weight_map"].values())))
|
||||
local state_json image_digest model_dir ple_path ple_bytes
|
||||
state_exports="$(python3 - "$LLM_PRIMARY_STATE" <<'PY'
|
||||
import json, shlex, sys
|
||||
state = json.load(open(sys.argv[1]))
|
||||
config = state.get("config") or {}
|
||||
if state.get("ready") is not True:
|
||||
sys.exit("R9V setup state is not ready")
|
||||
for key in ("R9V_IMAGE", "R9V_MODEL_DIR", "R9V_PLE_PATH", "R9V_PLE_EXPECTED_BYTES",
|
||||
"R9V_TARGET_REL", "R9V_TARGET_SHARD2_REL", "R9V_TARGET_SHARD3_REL", "R9V_MMPROJ_REL"):
|
||||
print(f"{key}={shlex.quote(config.get(key, ''))}")
|
||||
PY
|
||||
)" || return 1
|
||||
have_shards="$(find "$LLM_PRIMARY_ROOT" -maxdepth 1 -name '*.safetensors' | wc -l)"
|
||||
if [[ -z "$want_shards" || "$have_shards" != "$want_shards" ]]; then
|
||||
echo "ERROR: payload incomplete at $LLM_PRIMARY_ROOT (have $have_shards shards, index names $want_shards)" >&2
|
||||
echo "frank-primary: run scripts/download-frank-primary-fp8.sh on this host" >&2
|
||||
eval "$state_exports"
|
||||
if [[ -z "$R9V_IMAGE" || -z "$R9V_MODEL_DIR" || -z "$R9V_PLE_PATH" ]]; then
|
||||
echo "ERROR: R9V setup state is missing image/model/PLE paths" >&2
|
||||
return 1
|
||||
fi
|
||||
if ! podman images --format '{{.RepoDigests}}' | grep -qF "${R9V_IMAGE#sha256:}"; then
|
||||
echo "ERROR: pinned R9V runtime image absent from rootless storage: $R9V_IMAGE" >&2
|
||||
echo "frank-primary: load the image bundle (./r9v setup ...)" >&2
|
||||
return 1
|
||||
fi
|
||||
if [[ -n "$R9V_PLE_EXPECTED_BYTES" ]]; then
|
||||
ple_bytes="$(stat -c %s "$R9V_PLE_PATH" 2>/dev/null || echo 0)"
|
||||
if [[ "$ple_bytes" != "$R9V_PLE_EXPECTED_BYTES" ]]; then
|
||||
echo "ERROR: PLE payload wrong size: $R9V_PLE_PATH (expected $R9V_PLE_EXPECTED_BYTES, found $ple_bytes)" >&2
|
||||
echo "frank-primary: re-run the PLE derivation (./r9v setup ...)" >&2
|
||||
return 1
|
||||
fi
|
||||
fi
|
||||
local rel
|
||||
for rel in "$R9V_TARGET_REL" "$R9V_TARGET_SHARD2_REL" "$R9V_TARGET_SHARD3_REL" "$R9V_MMPROJ_REL"; do
|
||||
[[ -z "$rel" ]] && continue
|
||||
if [[ ! -f "$R9V_MODEL_DIR/$rel" ]]; then
|
||||
echo "ERROR: payload file missing: $R9V_MODEL_DIR/$rel" >&2
|
||||
echo "frank-primary: re-run the profile setup to fetch/verify the payload" >&2
|
||||
return 1
|
||||
fi
|
||||
done
|
||||
|
||||
# A stale container with the same name makes `podman run --name` fail at
|
||||
# start; remove any leftover from a failed previous attempt.
|
||||
@@ -1236,8 +1264,9 @@ PY
|
||||
run_privileged systemctl daemon-reload
|
||||
run_privileged systemctl enable frank-primary.service
|
||||
run_privileged systemctl restart frank-primary.service
|
||||
# Cold start: triton/inductor compile on first boot plus reading+pinning
|
||||
# ~173 GiB of weights. Parity with every predecessor on this port.
|
||||
# Cold start: the launcher's preflight doctor plus payload page-in
|
||||
# (~93 GiB cold; expert cache fills after /health). Parity with every
|
||||
# predecessor on this port.
|
||||
wait_for_health frank-primary http://127.0.0.1:7770/health 1800 || return 1
|
||||
# False-green hardening (the 2026-09-26 lesson): a bare curl against the
|
||||
# port cannot tell WHO answers — a stray probe holding :7770 satisfies
|
||||
|
||||
Reference in New Issue
Block a user