swift15 cutover: AGENTS.md + runbook + log + fleet probes + KLD gate shape fix

- AGENTS.md: fleet table row + frank-primary section rewritten for the
  GPTQ w4 chain (1.0.13 serve/convert, 1.2.0 calib, int8 KV, vram pair).
- runbook: throughput gate PASS (136.0 t/s median @ 44.5k, 4.5x bar),
  fleet probes PASS, control baselines recorded.
- log.md: 2026-10-08 campaign entry with the four measured engine laws.
- kld-gate: shape matched to the reference recording, then reshaped for
  the w4 MNBT<=2048 file-tier law (pool 40960).
- fleet-probes-swift15.sh: tools/reasoning/response_format/vision walk.
This commit is contained in:
Frank
2026-10-08 04:41:07 -07:00
parent cc0fdd15a1
commit 1aef7418ad
6 changed files with 192 additions and 84 deletions
+9 -10
View File
@@ -24,8 +24,8 @@ UNIT="$REPO_ROOT/scripts/frank-primary.service"
SERVE="$REPO_ROOT/scripts/serve-frank-primary.sh"
ENV_FILE="$REPO_ROOT/scripts/frank-primary.env"
REMOTE_DEPLOY="$REPO_ROOT/scripts/deploy-remote.sh"
DOWNLOAD="$REPO_ROOT/scripts/download-frank-primary.sh"
BUILD="$REPO_ROOT/scripts/build-frank-primary-rad.sh"
DOWNLOAD="$REPO_ROOT/scripts/download-frank-primary-swift15.sh"
BUILD="$REPO_ROOT/scripts/convert-swift15-w4dn8.sh"
HFGET="$REPO_ROOT/scripts/hfget.sh"
TEMPLATE="$REPO_ROOT/scripts/qwen38-froggeric-v22.5.jinja"
@@ -239,18 +239,17 @@ TEMPLATE="$REPO_ROOT/scripts/qwen38-froggeric-v22.5.jinja"
}
@test "the model id matches the payload's build and fetch scripts" {
# The payload dir/file are the build script's output layout; the fetch
# script must name the repo the build stages from.
# The payload dir/file are the convert script's output layout; the fetch
# script must name the repo the convert stages from. (FP8-native era,
# the rollback payload, keeps its own trio: build-frank-primary-rad.sh +
# download-frank-primary.sh.)
grep -q '^FRANK_PRIMARY_MODEL_DIR=/home/dank/models/rad$' "$ENV_FILE"
grep -q '^FRANK_PRIMARY_MODEL_FILE=qwen4exp-fp8-native.rad$' "$ENV_FILE"
grep -q 'qwen4exp-fp8-native.rad' "$BUILD"
grep -q 'Qwen/Qwen3.8-Flash-Next-FP8' "$DOWNLOAD"
grep -q '^FRANK_PRIMARY_MODEL_FILE=qwen4exp-swift15-w4dn8-i8-hc8m.rad$' "$ENV_FILE"
grep -q 'qwen4exp-swift15-w4dn8-i8-hc8m.rad' "$BUILD"
grep -q 'ukisai/Swift1.5-Qwen3.8-Flash-Next' "$DOWNLOAD"
grep -q 'hfget.sh' "$DOWNLOAD"
# The repo is UNGATED — no token may be required on the fetch path.
! grep -q 'HF_TOKEN' "$DOWNLOAD"
# The staging step drops quantization_config (the descriptor fix) —
# document it where it happens.
grep -q 'quantization_config' "$BUILD"
}
@test "no bare HIP-reserved env var is defined" {