dank/serverAppConfigs
1
0
Fork 0
Code Issues 6 Pull Requests Actions Packages Projects Releases Wiki Activity

merge: swift15-radiance-w4dn8 — frank-primary GPTQ w4 (Swift1.5)

Browse Source 
Conflict resolved: frank-primary row from the branch (w4 chain),
frank-secondary row from main (Qwen3.5-9B swap of 2026-10-07).
This commit is contained in:
Frank
2026-10-08 04:46:11 -07:00
parent fa5a444b64 1aef7418ad
commit 02fa1e22ae
24 changed files with 1779 additions and 84 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tests/frank_primary_unit.bats
+18 -16
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"
@@ -118,19 +118,21 @@ TEMPLATE="$REPO_ROOT/scripts/qwen38-froggeric-v22.5.jinja"
grep -q '^FRANK_PRIMARY_MAX_MODEL_LEN=200000$' "$ENV_FILE"
ml=$(awk -F= '/^FRANK_PRIMARY_MAX_MODEL_LEN=/{print $2}' "$ENV_FILE")
[ "$ml" -ge 177356 ]
# First-boot conservative shape (Frank's call): 2 decode slots. The
# fused TP all-reduce is declared over seqs x (1 + spec) rows = 8.
grep -q '^FRANK_PRIMARY_MAX_SEQS=2$' "$ENV_FILE"
# Decode-sweep shape (2026-10-06): 3 slots, spec depth 2 — the measured
# optimum (33.06 t/s). The fused TP all-reduce is declared over
# seqs x (1 + spec) rows = 9.
grep -q '^FRANK_PRIMARY_MAX_SEQS=3$' "$ENV_FILE"
grep -q '^FRANK_PRIMARY_TP=2$' "$ENV_FILE"
grep -q '^FRANK_PRIMARY_TP_WIRE=wht6$' "$ENV_FILE"
grep -q '^FRANK_PRIMARY_SPEC_TOKENS=3$' "$ENV_FILE"
grep -q '^FRANK_PRIMARY_SPEC_TOKENS=2$' "$ENV_FILE"
# Native-precision economics: the expert pool is per rank (56.4 GiB
# slice per rank at TP2), the PLE ngram table is pinned in host RAM per
# Frank's law, KV is fp8, the ratio is the publisher's production
# value.
grep -q '^FRANK_PRIMARY_PLACEMENT=expert_tiered$' "$ENV_FILE"
grep -q '^FRANK_PRIMARY_HOST_POOL_MIB=40960$' "$ENV_FILE"
grep -q '^FRANK_PRIMARY_EXPERT_VS_CACHE=0.82$' "$ENV_FILE"
grep -q '^FRANK_PRIMARY_VRAM_WEIGHTS_MIB=[1-9]' "$ENV_FILE"
grep -q '^FRANK_PRIMARY_VRAM_KV_MIB=[1-9]' "$ENV_FILE"
grep -q '^FRANK_PRIMARY_KV_DTYPE=fp8$' "$ENV_FILE"
grep -q '^FRANK_PRIMARY_NGRAM_PLACEMENT=ram$' "$ENV_FILE"
# Prefix cache tiers (publisher pattern; disk tier sized for 2 slots).
@@ -162,7 +164,8 @@ TEMPLATE="$REPO_ROOT/scripts/qwen38-froggeric-v22.5.jinja"
grep -q -- '--max-model-len "$FRANK_PRIMARY_MAX_MODEL_LEN"' "$SERVE"
grep -q -- '--placement "$FRANK_PRIMARY_PLACEMENT"' "$SERVE"
grep -q -- '--host-pool-mib "$FRANK_PRIMARY_HOST_POOL_MIB"' "$SERVE"
grep -q -- '--expert-vs-cache-ratio "$FRANK_PRIMARY_EXPERT_VS_CACHE"' "$SERVE"
grep -q -- '--vram-weights-mib "$FRANK_PRIMARY_VRAM_WEIGHTS_MIB"' "$SERVE"
grep -q -- '--vram-kv-mib "$FRANK_PRIMARY_VRAM_KV_MIB"' "$SERVE"
grep -q -- '--kv-cache-dtype "$FRANK_PRIMARY_KV_DTYPE"' "$SERVE"
grep -q -- '--prefix-cache-host-mib "$FRANK_PRIMARY_PREFIX_HOST_MIB"' "$SERVE"
grep -q -- '--prefix-cache-disk-mib "$FRANK_PRIMARY_PREFIX_DISK_MIB"' "$SERVE"
@@ -236,18 +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" {