llm: retire the trio service names — fleet services renamed to frank-archon/frank-dragoon/frank-zealot
The 2026-10-09 wire aliases become the service names everywhere: systemd units, serve scripts, env files and FRANK_* variables, deploy-plan/deploy-remote service keys, container names, Prometheus job names + alert rules, Grafana dashboard queries, bats seams, runbook filenames, homepage/AGENTS lore, and historical prose. Rollback tags renamed in lockstep. Residue in the tree: zero. Retired frank-medium/small/npu names are history and stay. Known casualty: scripts/patches/*.patch context lines were rewritten; those retired-era vLLM-fork patches no longer apply byte-exact.
This commit is contained in:
Frank
+32
-32
@@ -1,19 +1,19 @@
|
||||
#!/usr/bin/env bash
|
||||
# frank-primary-arms.sh — run a SEQUENCE of frank-primary bench arms and keep
|
||||
# frank-archon-arms.sh — run a SEQUENCE of frank-archon bench arms and keep
|
||||
# every arm's evidence. Runs on the operator box; each arm is one full window
|
||||
# of ./autoresearch.sh (stop+mask -> boot the arm as the service -> measure ->
|
||||
# restore production and verify), so the fleet is only ever down for one arm at
|
||||
# a time and the production unit is back up between arms.
|
||||
#
|
||||
# An arm is the repo's own frank-primary.env plus an OVERLAY of engine knobs
|
||||
# An arm is the repo's own frank-archon.env plus an OVERLAY of engine knobs
|
||||
# appended after it (later assignment wins when the serve script sources it),
|
||||
# staged through FRANK_PRIMARY_AR_ENV_FILE so the checkout is never mutated and
|
||||
# staged through FRANK_ARCHON_AR_ENV_FILE so the checkout is never mutated and
|
||||
# each arm gets its own fingerprint (the memo can never answer one arm with
|
||||
# another arm's numbers).
|
||||
#
|
||||
# Usage: scripts/autoresearch/frank-primary-arms.sh [arm ...]
|
||||
# scripts/autoresearch/frank-primary-arms.sh --list
|
||||
# Output, under /tmp/frank-primary-arms-<UTC stamp>/ (override with ARMS_DIR):
|
||||
# Usage: scripts/autoresearch/frank-archon-arms.sh [arm ...]
|
||||
# scripts/autoresearch/frank-archon-arms.sh --list
|
||||
# Output, under /tmp/frank-archon-arms-<UTC stamp>/ (override with ARMS_DIR):
|
||||
#
|
||||
# <arm>.out full autoresearch output (metrics + engine evidence)
|
||||
# <arm>.env the exact staged env
|
||||
@@ -26,8 +26,8 @@ set -uo pipefail
|
||||
|
||||
SCRIPT_DIR="$(cd -- "$(dirname -- "${BASH_SOURCE[0]}")" && pwd)"
|
||||
REPO="$(cd -- "$SCRIPT_DIR/../.." && pwd)"
|
||||
BASE_ENV="$REPO/scripts/frank-primary.env"
|
||||
ARMS_DIR="${ARMS_DIR:-/tmp/frank-primary-arms-$(date -u +%Y%m%dT%H%M%SZ)}"
|
||||
BASE_ENV="$REPO/scripts/frank-archon.env"
|
||||
ARMS_DIR="${ARMS_DIR:-/tmp/frank-archon-arms-$(date -u +%Y%m%dT%H%M%SZ)}"
|
||||
|
||||
# --- arms ------------------------------------------------------------------
|
||||
# baseline: the shipped shape E, measured with THIS harness so the comparison is
|
||||
@@ -45,18 +45,18 @@ LADDER3='{"cudagraph_capture_sizes":[4,8,12],"max_cudagraph_capture_size":12,"in
|
||||
# the engine as {temperature:0.7}.
|
||||
GEN07='{"temperature":0.7}'
|
||||
OVER_B=(
|
||||
"FRANK_PRIMARY_SPEC='$SPEC3'"
|
||||
"FRANK_PRIMARY_COMPCONFIG='$LADDER3'"
|
||||
'FRANK_PRIMARY_GEN_CONFIG='"'$GEN07'"
|
||||
"FRANK_ARCHON_SPEC='$SPEC3'"
|
||||
"FRANK_ARCHON_COMPCONFIG='$LADDER3'"
|
||||
'FRANK_ARCHON_GEN_CONFIG='"'$GEN07'"
|
||||
)
|
||||
# B2: identical to B with the default (7.60 GiB) overhead, i.e. precise memory
|
||||
# OFF. It is the fallback if B dies at graph capture, and it prices the arena
|
||||
# that precise memory buys (7,522 slots -> ~6,496).
|
||||
OVER_B2=(
|
||||
"FRANK_PRIMARY_SPEC='$SPEC3'"
|
||||
"FRANK_PRIMARY_COMPCONFIG='$LADDER3'"
|
||||
'FRANK_PRIMARY_GEN_CONFIG='"'$GEN07'"
|
||||
'FRANK_PRIMARY_PRECISE_MEMORY='
|
||||
"FRANK_ARCHON_SPEC='$SPEC3'"
|
||||
"FRANK_ARCHON_COMPCONFIG='$LADDER3'"
|
||||
'FRANK_ARCHON_GEN_CONFIG='"'$GEN07'"
|
||||
'FRANK_ARCHON_PRECISE_MEMORY='
|
||||
)
|
||||
# C: the vendor's concurrency shape — SEQS 16 with the [4..32] ladder and util
|
||||
# 0.95. This is also the direct test of the theory that pinning the capture
|
||||
@@ -64,12 +64,12 @@ OVER_B2=(
|
||||
# the constant 3, which is NOT in the default ladder; 4 is).
|
||||
LADDER16='{"cudagraph_capture_sizes":[4,8,12,16,20,24,28,32],"max_cudagraph_capture_size":32,"inductor_compile_config":{"combo_kernels":false,"benchmark_combo_kernel":false}}'
|
||||
OVER_C=(
|
||||
"FRANK_PRIMARY_SPEC='$SPEC3'"
|
||||
"FRANK_PRIMARY_COMPCONFIG='$LADDER16'"
|
||||
'FRANK_PRIMARY_GEN_CONFIG='"'$GEN07'"
|
||||
'FRANK_PRIMARY_SEQS=16'
|
||||
'FRANK_PRIMARY_MNBT=4096'
|
||||
'FRANK_PRIMARY_UTIL=0.95'
|
||||
"FRANK_ARCHON_SPEC='$SPEC3'"
|
||||
"FRANK_ARCHON_COMPCONFIG='$LADDER16'"
|
||||
'FRANK_ARCHON_GEN_CONFIG='"'$GEN07'"
|
||||
'FRANK_ARCHON_SEQS=16'
|
||||
'FRANK_ARCHON_MNBT=4096'
|
||||
'FRANK_ARCHON_UTIL=0.95'
|
||||
)
|
||||
|
||||
# D/E: the CONTEXT arms. Measured 2026-10-02 (arms run 20261002T233855Z): the
|
||||
@@ -83,11 +83,11 @@ OVER_C=(
|
||||
# D is arm B with EXACTLY ONE variable changed (the KV bytes), so its result
|
||||
# says whether the 4k-depth collapse (B 23.09 vs baseline 33.99) was KV or the
|
||||
# batch shape.
|
||||
KV401K='FRANK_PRIMARY_KV_BYTES=4050000000'
|
||||
KV401K='FRANK_ARCHON_KV_BYTES=4050000000'
|
||||
OVER_D=(
|
||||
"FRANK_PRIMARY_SPEC='$SPEC3'"
|
||||
"FRANK_PRIMARY_COMPCONFIG='$LADDER3'"
|
||||
'FRANK_PRIMARY_GEN_CONFIG='"'$GEN07'"
|
||||
"FRANK_ARCHON_SPEC='$SPEC3'"
|
||||
"FRANK_ARCHON_COMPCONFIG='$LADDER3'"
|
||||
'FRANK_ARCHON_GEN_CONFIG='"'$GEN07'"
|
||||
"$KV401K"
|
||||
)
|
||||
# E: D with C's max_num_batched_tokens (4096 — C is the only arm that did NOT
|
||||
@@ -97,12 +97,12 @@ OVER_D=(
|
||||
# only 0.32 GiB above the allowance while the CUDA-graph cost is an ANALYTIC
|
||||
# estimate (C's was 1.47 GiB over 24 graphs), so it is measured, not assumed.
|
||||
OVER_E=(
|
||||
"FRANK_PRIMARY_SPEC='$SPEC3'"
|
||||
"FRANK_PRIMARY_COMPCONFIG='$LADDER3'"
|
||||
'FRANK_PRIMARY_GEN_CONFIG='"'$GEN07'"
|
||||
"FRANK_ARCHON_SPEC='$SPEC3'"
|
||||
"FRANK_ARCHON_COMPCONFIG='$LADDER3'"
|
||||
'FRANK_ARCHON_GEN_CONFIG='"'$GEN07'"
|
||||
"$KV401K"
|
||||
'FRANK_PRIMARY_MNBT=4096'
|
||||
'FRANK_PRIMARY_UTIL=0.99'
|
||||
'FRANK_ARCHON_MNBT=4096'
|
||||
'FRANK_ARCHON_UTIL=0.99'
|
||||
)
|
||||
|
||||
arm_overlay() {
|
||||
@@ -142,7 +142,7 @@ for arm in "${ARMS[@]}"; do
|
||||
# holds JSON must still be one valid JSON object after the file is SOURCED
|
||||
# (that is the step that silently eats unquoted braces).
|
||||
if ! bash -c 'set -a; . "$1" >/dev/null; set +a
|
||||
for k in FRANK_PRIMARY_SPEC FRANK_PRIMARY_COMPCONFIG FRANK_PRIMARY_GEN_CONFIG; do
|
||||
for k in FRANK_ARCHON_SPEC FRANK_ARCHON_COMPCONFIG FRANK_ARCHON_GEN_CONFIG; do
|
||||
v="${!k:-}"
|
||||
[ -n "$v" ] || continue
|
||||
case "$v" in
|
||||
@@ -158,7 +158,7 @@ for arm in "${ARMS[@]}"; do
|
||||
fi
|
||||
|
||||
echo "[arms] === $arm: opening window $(date -u +%H:%M:%S)Z ===" >&2
|
||||
FRANK_PRIMARY_AR_ENV_FILE="$ARMS_DIR/$arm.env" \
|
||||
FRANK_ARCHON_AR_ENV_FILE="$ARMS_DIR/$arm.env" \
|
||||
"$REPO/autoresearch.sh" >"$ARMS_DIR/$arm.out" 2>&1
|
||||
rc=$?
|
||||
echo "$rc" >"$ARMS_DIR/$arm.rc"
|
||||
+2
-2
@@ -1,5 +1,5 @@
|
||||
#!/usr/bin/env python3
|
||||
"""frank-primary decode measurement — runs INSIDE the engine container.
|
||||
"""frank-archon decode measurement — runs INSIDE the engine container.
|
||||
|
||||
The method is the fleet's established one (the 2026-09-29 / 2026-10-01
|
||||
tuning campaigns, /home/dank/mtp_measure.py): SSE chunk counting is invalid
|
||||
@@ -28,7 +28,7 @@ Workload (fixed, deterministic, offline):
|
||||
|
||||
Env:
|
||||
AR_BASE endpoint (default http://127.0.0.1:7770)
|
||||
AR_MODEL served name (default frank-primary)
|
||||
AR_MODEL served name (default frank-archon)
|
||||
AR_PROMPT_CEILING hard prompt ceiling in tokens (default 100000)
|
||||
AR_TEMPS comma-separated sampling temperatures (default "0,0.7")
|
||||
|
||||
+14
-14
@@ -1,5 +1,5 @@
|
||||
#!/usr/bin/env bash
|
||||
# frank-primary-window.sh — one full bench window for frank-primary, run ON
|
||||
# frank-archon-window.sh — one full bench window for frank-archon, run ON
|
||||
# DANKSERVER as the deploy user (invoked over ssh by ./autoresearch.sh).
|
||||
#
|
||||
# Discipline (AGENTS.md Benchmarking Policy): the production unit is
|
||||
@@ -12,9 +12,9 @@
|
||||
#
|
||||
# Staging layout (created by the orchestrator, ephemeral — never a config
|
||||
# source; the repo checkout is):
|
||||
# /home/dank/.autoresearch-frank-primary/
|
||||
# /home/dank/.autoresearch-frank-archon/
|
||||
# serve.sh staged candidate serve script
|
||||
# frank-primary.env staged candidate env (the candidate knobs)
|
||||
# frank-archon.env staged candidate env (the candidate knobs)
|
||||
# measure.py the in-container measure client
|
||||
# hash candidate fingerprint
|
||||
# run.json result (metrics + boot + kv + fingerprint)
|
||||
@@ -27,16 +27,16 @@
|
||||
# outcome; a failed restore forces exit 1).
|
||||
set -uo pipefail
|
||||
|
||||
STAGE="${FRANK_PRIMARY_AR_STAGE:-/home/dank/.autoresearch-frank-primary}"
|
||||
UNIT="${FRANK_PRIMARY_AR_UNIT:-frank-primary}"
|
||||
CTR="${FRANK_PRIMARY_AR_CTR:-frank-primary-qwen}"
|
||||
STAGE="${FRANK_ARCHON_AR_STAGE:-/home/dank/.autoresearch-frank-archon}"
|
||||
UNIT="${FRANK_ARCHON_AR_UNIT:-frank-archon}"
|
||||
CTR="${FRANK_ARCHON_AR_CTR:-frank-archon-qwen}"
|
||||
HEALTH_URL="http://127.0.0.1:7770/health"
|
||||
MODELS_URL="http://127.0.0.1:7770/v1/models"
|
||||
BOOT_TIMEOUT="${FRANK_PRIMARY_AR_BOOT_TIMEOUT:-1200}"
|
||||
RESTORE_TIMEOUT="${FRANK_PRIMARY_AR_RESTORE_TIMEOUT:-1200}"
|
||||
MEASURE_TIMEOUT="${FRANK_PRIMARY_AR_MEASURE_TIMEOUT:-1800}"
|
||||
SERVED="$(sed -n 's/^FRANK_PRIMARY_SERVED_NAME=//p' "$STAGE/frank-primary.env" 2>/dev/null | head -1)"
|
||||
SERVED="${SERVED:-frank-primary}"
|
||||
BOOT_TIMEOUT="${FRANK_ARCHON_AR_BOOT_TIMEOUT:-1200}"
|
||||
RESTORE_TIMEOUT="${FRANK_ARCHON_AR_RESTORE_TIMEOUT:-1200}"
|
||||
MEASURE_TIMEOUT="${FRANK_ARCHON_AR_MEASURE_TIMEOUT:-1800}"
|
||||
SERVED="$(sed -n 's/^FRANK_ARCHON_SERVED_NAME=//p' "$STAGE/frank-archon.env" 2>/dev/null | head -1)"
|
||||
SERVED="${SERVED:-frank-archon}"
|
||||
|
||||
RESTORED=0
|
||||
|
||||
@@ -72,7 +72,7 @@ capture_bench_failure() {
|
||||
echo "=== staged serve.out (tail 60) ==="
|
||||
tail -60 "$STAGE/serve.out" 2>/dev/null || true
|
||||
echo "=== engine log (tail 60) ==="
|
||||
tail -60 /home/dank/logs/frank_primary.log 2>/dev/null || true
|
||||
tail -60 /home/dank/logs/frank_archon.log 2>/dev/null || true
|
||||
} >"$STAGE/fail.log" 2>&1 || true
|
||||
grep -E 'OutOfMemory|Tried to allocate|Engine core initialization failed|Error|error' \
|
||||
"$STAGE/fail.log" 2>/dev/null | tail -25 >&2 || true
|
||||
@@ -114,7 +114,7 @@ trap 'restore; rc=$?; [ "$rc" -ne 0 ] && exit 1' EXIT
|
||||
|
||||
main() {
|
||||
local f
|
||||
for f in serve.sh frank-primary.env measure.py hash; do
|
||||
for f in serve.sh frank-archon.env measure.py hash; do
|
||||
[ -f "$STAGE/$f" ] || { log "staged file missing: $STAGE/$f"; exit 1; }
|
||||
done
|
||||
mkdir -p "$STAGE/last"
|
||||
@@ -133,7 +133,7 @@ main() {
|
||||
|
||||
t0="$(date +%s)"
|
||||
log "starting bench instance from staged config (fingerprint $(tr -d '[:space:]' <"$STAGE/hash"))"
|
||||
FRANK_PRIMARY_ENV_FILE="$STAGE/frank-primary.env" \
|
||||
FRANK_ARCHON_ENV_FILE="$STAGE/frank-archon.env" \
|
||||
setsid nohup bash "$STAGE/serve.sh" >"$STAGE/serve.out" 2>&1 </dev/null &
|
||||
echo "$!" >"$STAGE/serve.pid"
|
||||
|
||||
Reference in New Issue
Block a user