llm(frank-archon): swap payload to the publisher's iq4r .rad, shape verbatim
Model swap on the radiance endpoint: MODEL_FILE moves from the in-house qwen4exp-swift15-w4dn8-i8-hc8m.rad (116,416 MiB) to the engine author's published qwen3.8-next-flash-fp8-iq4r-moe.rad (116,322 MiB, official Qwen3.8-Flash-Next bf16 -> 4-bit non-uniform codebook experts + int8 trunk, card KL 0.0789 / top-1 92.85 % vs bf16). NO argument changed: 25600/5120 vram pair, 44928 host pool, fp8 KV, 3 x 200000, MTP depth 2, wht6, MNBT 2048, froggeric v22.5 — the 2026-10-13 shape carries verbatim. New fetch script scripts/download-frank-archon-iq4r.sh (hfget + exact byte count 121,969,901,568 + LFS sha256, --verify-only default, ungated, no token on the command line). Unit/serve/deployer lore re-keyed; the seam pins the new payload id + sha256 and keeps the w4dn8 rollback provenance. Homepage card points at the publisher repo. Rollback: revert this commit (w4dn8 .rad stays on disk). The fp8-native rad was deleted from dankserver 2026-10-15 (Frank's one-time rm, volume for this payload); rebuild path documented.
This commit is contained in:
Frank
@@ -1277,11 +1277,14 @@ deploy_llm_zealot() {
|
||||
}
|
||||
|
||||
# deploy_llm_archon — frank-archon is the radiance engine (StillDeadcode,
|
||||
# digest-pinned stilldeadcode/radiance image) serving the OFFICIAL
|
||||
# Qwen/Qwen3.8-Flash-Next-FP8 at native block-FP8 precision from the
|
||||
# rad-convert container qwen4exp-fp8-native.rad, on BOTH R9700s (TP=2) as a
|
||||
# digest-pinned stilldeadcode/radiance image) serving the PUBLISHER's
|
||||
# 4-bit-codebook container of the official Qwen/Qwen3.8-Flash-Next
|
||||
# (qwen3.8-next-flash-fp8-iq4r-moe.rad, fetched by
|
||||
# scripts/download-frank-archon-iq4r.sh) on BOTH R9700s (TP=2) as a
|
||||
# ROOT unit whose serve script drives `podman run` directly (the engine is
|
||||
# the image entrypoint; the image lives in dank's rootless podman storage).
|
||||
# 2026-10-15 payload swap from the in-house w4dn8 (payload on disk =
|
||||
# rollback).
|
||||
# 2026-10-05 cutover from FreeToken (pre-cutover tag
|
||||
# frank-archon-freetoken-pr587-20261005); before that, the tcclaviger vLLM
|
||||
# fork (tag frank-archon-vllm-shapeG-20261003). Same port and alias; the
|
||||
@@ -1290,7 +1293,7 @@ deploy_llm_zealot() {
|
||||
# Gates: the image must exist under its digest ref in dank's rootless
|
||||
# storage (FRANK_ARCHON_IMAGE), the .rad container file must exist at the
|
||||
# env's size floor (FRANK_ARCHON_MODEL_FILE >= FRANK_ARCHON_RAD_MIN_MIB —
|
||||
# a truncated convert is a guaranteed long-timeout boot), and the unit env
|
||||
# a truncated fetch is a guaranteed long-timeout boot), and the unit env
|
||||
# must be complete. Per-file sha256 verification is the fetch script's job
|
||||
# at download time and rad-convert/rad-info's job at build time, never
|
||||
# re-hashed here.
|
||||
@@ -1325,13 +1328,13 @@ deploy_llm_archon() {
|
||||
fi
|
||||
if [[ ! -f "$model_dir/$model_file" ]]; then
|
||||
echo "ERROR: .rad container missing: $model_dir/$model_file" >&2
|
||||
echo "frank-archon: run scripts/build-frank-archon-rad.sh" >&2
|
||||
echo "frank-archon: run scripts/download-frank-archon-iq4r.sh --fetch" >&2
|
||||
return 1
|
||||
fi
|
||||
mib=$(( $(stat -c %s "$model_dir/$model_file") / 1048576 ))
|
||||
if [[ "$mib" -lt "$rad_min" ]]; then
|
||||
echo "ERROR: .rad container too small: $model_dir/$model_file is ${mib} MiB, want >= $rad_min" >&2
|
||||
echo "frank-archon: rebuild it (scripts/build-frank-archon-rad.sh --force)" >&2
|
||||
echo "frank-archon: re-fetch it (scripts/download-frank-archon-iq4r.sh --fetch; delete the staged file first if its sha256 failed)" >&2
|
||||
return 1
|
||||
fi
|
||||
|
||||
|
||||
Executable
+83
@@ -0,0 +1,83 @@
|
||||
#!/usr/bin/env bash
|
||||
# download-frank-archon-iq4r.sh — payload fetch/verify for the frank-archon
|
||||
# swap to the PUBLISHER's 4-bit-codebook container:
|
||||
# StillDeadcode/qwen3.8-next-flash-fp8-iq4r-moe — the official
|
||||
# Qwen/Qwen3.8-Flash-Next bf16 checkpoint rad-converted by the engine's own
|
||||
# author into ONE .rad: routed experts as 4-bit codes into a 16-level
|
||||
# non-uniform codebook (Walsh–Hadamard rotation, GPTQ + coordinate-descent,
|
||||
# 10M-token calibration), ten bf16-protected experts per layer, int8 trunk +
|
||||
# lm_head, fp8 HC mixtures, the PLE n-gram table at fp8 fixed scale, the MTP
|
||||
# head, and the bf16 vision tower. File:
|
||||
# qwen3.8-next-flash-fp8-iq4r-moe.rad — 121,969,901,568 B (113.6 GiB,
|
||||
# 116,322 MiB), card KL 0.0789 all-tokens / top-1 92.85 % vs bf16.
|
||||
# Repo is UNGATED — no token needed (never put one on the command line).
|
||||
#
|
||||
# bash scripts/download-frank-archon-iq4r.sh --fetch resume/complete
|
||||
# bash scripts/download-frank-archon-iq4r.sh verify only
|
||||
#
|
||||
# Fetch uses the vendored scripts/hfget.sh (curl+jq only): per-file size
|
||||
# checks against the Hub listing, `-C -` resume, disk-fit gate. The side
|
||||
# files (LICENSE, README, the w4nl recipe) stay in the staging dir as
|
||||
# provenance; the serve gate mounts ONLY /home/dank/models/rad, so the
|
||||
# verified .rad alone moves into it.
|
||||
#
|
||||
# Verify (default) is the AGENTS.md law in two parts: the file lands at the
|
||||
# final path with the Hub's EXACT byte count, and its sha256 equals the
|
||||
# Hub's LFS oid. A truncated transfer is a guaranteed long-timeout boot
|
||||
# without this gate.
|
||||
set -euo pipefail
|
||||
|
||||
REPO="StillDeadcode/qwen3.8-next-flash-fp8-iq4r-moe"
|
||||
RAD_NAME="qwen3.8-next-flash-fp8-iq4r-moe.rad"
|
||||
STAGE="/home/dank/models/StillDeadcode/qwen3.8-next-flash-fp8-iq4r-moe"
|
||||
DEST="/home/dank/models/rad/$RAD_NAME"
|
||||
SIZE=121969901568
|
||||
SHA256="0af5e96244e80c21ac8edca1719dae49b8a201b94a2f3994c3e24026ceaa4d20"
|
||||
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
||||
|
||||
mode="verify"
|
||||
[[ "${1:-}" == "--fetch" ]] && mode="fetch"
|
||||
|
||||
if [[ "$mode" == "fetch" ]]; then
|
||||
# HFGET_JOBS=4 is hfget's default (a few streams saturate the link).
|
||||
bash "$SCRIPT_DIR/hfget.sh" "$REPO" "$STAGE" main
|
||||
|
||||
staged="$STAGE/$RAD_NAME"
|
||||
if [[ ! -f "$staged" ]]; then
|
||||
echo "FETCH FAILED: $staged absent after hfget" >&2
|
||||
exit 1
|
||||
fi
|
||||
got=$(stat -c %s "$staged")
|
||||
if [[ "$got" != "$SIZE" ]]; then
|
||||
echo "FETCH FAILED: staged .rad is $got B, want $SIZE B" >&2
|
||||
exit 1
|
||||
fi
|
||||
echo "staged .rad byte-exact ($SIZE B); hashing (one full read, minutes)"
|
||||
got_sha=$(sha256sum "$staged" | cut -d' ' -f1)
|
||||
if [[ "$got_sha" != "$SHA256" ]]; then
|
||||
echo "FETCH FAILED: sha256 $got_sha, want $SHA256 — DELETE the staged" \
|
||||
"file before re-fetching (curl -C - cannot repair a corrupt body)" >&2
|
||||
exit 1
|
||||
fi
|
||||
mkdir -p "$(dirname "$DEST")"
|
||||
mv "$staged" "$DEST"
|
||||
echo "payload placed: $DEST"
|
||||
fi
|
||||
|
||||
echo "verifying deployed payload: $DEST"
|
||||
if [[ ! -f "$DEST" ]]; then
|
||||
echo " BAD payload absent: $DEST" >&2
|
||||
exit 1
|
||||
fi
|
||||
got=$(stat -c %s "$DEST")
|
||||
if [[ "$got" != "$SIZE" ]]; then
|
||||
echo " BAD payload is $got B, want $SIZE B" >&2
|
||||
exit 1
|
||||
fi
|
||||
echo "byte-exact ($SIZE B); hashing (one full read, minutes)"
|
||||
got_sha=$(sha256sum "$DEST" | cut -d' ' -f1)
|
||||
if [[ "$got_sha" != "$SHA256" ]]; then
|
||||
echo " BAD sha256 $got_sha, want $SHA256" >&2
|
||||
exit 1
|
||||
fi
|
||||
echo "payload verified: $RAD_NAME, size and sha256 match the Hub LFS oid"
|
||||
+54
-34
@@ -1,7 +1,15 @@
|
||||
# frank-archon.env — radiance (StillDeadcode, Apache-2.0) serving
|
||||
# ukisai/Swift1.5-Qwen3.8-Flash-Next converted to GPTQ w4 (MODEL_FILE below,
|
||||
# built by scripts/convert-swift15-w4dn8.sh) on BOTH R9700s (TP=2),
|
||||
# dankserver :7770.
|
||||
# frank-archon.env — radiance (StillDeadcode, Apache-2.0) serving the
|
||||
# PUBLISHER's 4-bit-codebook container of the official Qwen/Qwen3.8-Flash-Next
|
||||
# (MODEL_FILE below, fetched by scripts/download-frank-archon-iq4r.sh) on
|
||||
# BOTH R9700s (TP=2), dankserver :7770.
|
||||
# 2026-10-15 PAYLOAD SWAP: the model moved from the in-house w4dn8 conversion
|
||||
# of the Swift1.5 finetune to the engine author's published container
|
||||
# qwen3.8-next-flash-fp8-iq4r-moe.rad (116,322 MiB, sha256-verified at fetch —
|
||||
# the w4dn8 measured 116,416 MiB, so this shape carries over with 94 MiB to
|
||||
# spare). NO argument changed: every number below is the 2026-10-13 shape,
|
||||
# kept verbatim. The swap commit is the rollback (the w4dn8 payload stays on
|
||||
# disk).
|
||||
|
||||
#
|
||||
# SHAPE (2026-10-13): THREE decode slots x 200,000 tokens, fp8 (quantized) KV,
|
||||
# with the per-card budget spent on resident experts: 25,600 MiB of slab +
|
||||
@@ -13,9 +21,11 @@
|
||||
# +25 % at the full window) while KV beyond the contract buys nothing.
|
||||
# Consequence, deliberate: a FOURTH full-height conversation does not fit this
|
||||
# pair, and the engine refuses it — it never truncates. See the KV block for the
|
||||
# arithmetic and the measured dtype law. The fp8-native payload this file was
|
||||
# written for is the rollback target and keeps its own trio under the
|
||||
# fp8-native runbook.
|
||||
# arithmetic and the measured dtype law. The w4dn8 payload is the swap
|
||||
# rollback and keeps its trio under the w4dn8 runbook; the fp8-native payload
|
||||
# that came before it was DELETED from disk 2026-10-15 (Frank's call, to free
|
||||
# the volume for this download — rebuildable via the fetch + build scripts
|
||||
# named in the fp8-native runbook).
|
||||
#
|
||||
# 2026-10-05 cutover from FreeToken (PR #587 ROCm, one card, experts in
|
||||
# pinned host RAM; git tag frank-archon-freetoken-pr587-20261005 is the
|
||||
@@ -30,20 +40,30 @@
|
||||
# (`X.weight_scale_inv` is the scale plane — checkpoint.h). The PLE n-gram
|
||||
# table (51B params, 47.7 GiB) is served from pinned host RAM via io_uring
|
||||
# reads — Frank's call: "Native FP8. Experts from ram. Pin the PLE to ram."
|
||||
# The 4-bit-codebook publisher shape (qwen3.8-next-flash-fp8-iq4r-moe.rad,
|
||||
# --host-pool-mib 12288) remains the documented fallback if the native
|
||||
# container proves unbootable.
|
||||
# THE 4-bit-codebook publisher shape is the DEPLOYED payload since
|
||||
# 2026-10-15. The card's own run line (--host-pool-mib 12288,
|
||||
# --expert-vs-cache-ratio 0.82, seqs 8, spec 3) is the publisher's
|
||||
# suggestion on 32 GB cards; this file's shape is the fleet's measured one.
|
||||
#
|
||||
# PAYLOAD: /home/dank/models/rad/qwen4exp-fp8-native.rad — a rad-convert
|
||||
# NO-RECIPE pure copy of the official 131-shard checkpoint (every weight
|
||||
# keeps its block-FP8 encoding; ~161 GiB). The convert runs against a
|
||||
# staging dir whose config.json drops `quantization_config`: the descriptor
|
||||
# string is only the plugin SELECTION key (spec §2.4 — exact match, no
|
||||
# fallback), and no shipped plugin claims (qwen4exp, "fp8"); the shipped
|
||||
# qwen4exp plugin claims (qwen4exp, "") which is what recipe-built
|
||||
# containers carry. Per-weight encodings are data, not the descriptor —
|
||||
# removing the key changes nothing about what the weights hold. Built by
|
||||
# scripts/build-frank-archon-rad.sh (staging + convert + rad-info).
|
||||
# PAYLOAD: /home/dank/models/rad/qwen3.8-next-flash-fp8-iq4r-moe.rad — the
|
||||
# official Qwen3.8-Flash-Next bf16 checkpoint rad-converted by the engine's
|
||||
# own author (recipe qwen4exp-w4nl64-i8-hc8m: experts as 4-bit codes into a
|
||||
# 16-level non-uniform codebook after a 128-point Walsh–Hadamard rotation,
|
||||
# GPTQ + 3 coordinate-descent sweeps on a 10M-token calibration, ten
|
||||
# bf16-protected experts per layer, int8 W8A8 trunk + lm_head, fp8 HC
|
||||
# mixtures, PLE n-gram fp8 fixed-scale, MTP head, bf16 vision tower; card KL
|
||||
# 0.0789 all-tokens / top-1 92.85 % vs bf16). Fetched byte-exact + sha256 by
|
||||
# scripts/download-frank-archon-iq4r.sh; the recipe/LICENSE stay in the
|
||||
# staging dir beside it as provenance. ROLLBACK: revert the swap commit — the
|
||||
# in-house qwen4exp-swift15-w4dn8-i8-hc8m.rad (scripts/convert-swift15-w4dn8.sh,
|
||||
# KLD-gated) stays on disk. Behind it, the fp8-native
|
||||
# qwen4exp-fp8-native.rad was DELETED from disk 2026-10-15 (Frank's call,
|
||||
# one-time rm, to free the volume for this payload); rebuild =
|
||||
# scripts/download-frank-archon.sh + scripts/build-frank-archon-rad.sh — a
|
||||
# NO-RECIPE rad-convert copy of the official 131-shard checkpoint under the
|
||||
# descriptor law (no shipped plugin claims (qwen4exp, "fp8"), so the staging
|
||||
# config.json drops quantization_config; per-weight encodings are data, not
|
||||
# the descriptor).
|
||||
#
|
||||
# SERVING FACTS (docs/GUIDE.md, docs/DOCKER.md, compose/flashnext.yaml):
|
||||
# - The HTTP listener binds AFTER the full load (main.cpp: engine.start()
|
||||
@@ -59,12 +79,12 @@
|
||||
# enable_thinking, preserve_thinking (core/server/oai.cpp:194-205) —
|
||||
# models.yml's extraBody set is fully inside it. Unknown params are
|
||||
# refused (400), which is why nothing unverified rides the wire.
|
||||
# - MTP: the official checkpoint carries the mtp.* head (3,101 tensors,
|
||||
# mtp_num_hidden_layers=1) and the plugin probes draft depth 3 — the
|
||||
# publisher's throughput peak for this model. Stated explicitly with
|
||||
# --num-speculative-tokens 3.
|
||||
# - MTP: the .rad carries the model's mtp.* head (the publisher's recipe
|
||||
# names the mtp.fc_hidden/fc_embedding/draft_head rules; card default
|
||||
# depth 3). Served at the depth named by FRANK_ARCHON_SPEC_TOKENS below —
|
||||
# the depth this shape's decode ladder was measured at.
|
||||
# - The fused TP all-reduce is declared over max-num-seqs x
|
||||
# (1 + --num-speculative-tokens) rows; 2 x 3 = 6 rows, under the 25-row
|
||||
# (1 + --num-speculative-tokens) rows; 3 x (1+2) = 9 rows, under the 25-row
|
||||
# exactness bound of the wht6 wire.
|
||||
# Engine pin: Codeberg tag v1.0.13 (commit 53282fa), Docker Hub tag 1.0.13,
|
||||
# index digest below. REJECTED UPGRADE: 1.2.0 (sha256:665775ed1d90de6dbb
|
||||
@@ -88,7 +108,7 @@ FRANK_ARCHON_IMAGE=stilldeadcode/radiance@sha256:4c3f484564bb2872784e46b0a59cbd7
|
||||
# .rad files; the raw HF download and its staging dir live beside it and
|
||||
# are never mounted.
|
||||
FRANK_ARCHON_MODEL_DIR=/home/dank/models/rad
|
||||
FRANK_ARCHON_MODEL_FILE=qwen4exp-swift15-w4dn8-i8-hc8m.rad
|
||||
FRANK_ARCHON_MODEL_FILE=qwen3.8-next-flash-fp8-iq4r-moe.rad
|
||||
FRANK_ARCHON_STATE_DIR=/home/dank/radiance-state
|
||||
# The state dir's tune/ subdirectory holds rad-tune's kernel-selection
|
||||
# cache (the engine's selector reads $RADIANCE_HOME/tune/<machine>.tune
|
||||
@@ -242,9 +262,10 @@ FRANK_ARCHON_VRAM_KV_MIB=5120
|
||||
# ledgers' `kv tier transfer` lines), so the host tier below parks twice as
|
||||
# many conversations as it did at bf16 — no re-size needed to park three slots.
|
||||
FRANK_ARCHON_KV_DTYPE=fp8
|
||||
# Spec decode: the checkpoint's own MTP head at the publisher's depth-3
|
||||
# operating point (probe() returns 3 when mtp_num_hidden_layers > 0; the
|
||||
# flag states it so the ledger records the intent).
|
||||
# Spec decode: the checkpoint's own MTP head, served at depth 2 — the
|
||||
# publisher's card ships depth 3 as its peak; this fleet's ladder was
|
||||
# measured at 2 and the swap keeps every argument, so 2 stays (rows
|
||||
# 3 x (1+2) = 9, inside the wht6 25-row exactness bound).
|
||||
FRANK_ARCHON_SPEC_TOKENS=2
|
||||
FRANK_ARCHON_MAX_BATCHED_TOKENS=2048
|
||||
# Prefix cache tiers (publisher pattern). The host tier is sized in ENTRIES,
|
||||
@@ -278,9 +299,8 @@ FRANK_ARCHON_TTM_TARGET_MIB=204800
|
||||
# multi-flag values as one string; the serve script expands it unquoted on
|
||||
# purpose.
|
||||
FRANK_ARCHON_EXTRA_ARGS=
|
||||
# The .rad's minimum size in MiB (deployer gate; a truncated convert is a
|
||||
# guaranteed long-timeout boot instead of a fast failure). The converted
|
||||
# container measured 177,109 MiB (1,857,127,997,440 B = 173.0 GiB; the
|
||||
# plan-only estimate 172.76 GiB covers the data planes but not the metadata
|
||||
# tail) - floor sits just under the payload.
|
||||
# The .rad's minimum size in MiB (deployer gate; a truncated fetch is a
|
||||
# guaranteed long-timeout boot instead of a fast failure). The deployed
|
||||
# publisher container measures 116,322 MiB (121,969,901,568 B); the
|
||||
# in-house w4dn8 rollback measured 116,416 MiB. Floor sits just under both.
|
||||
FRANK_ARCHON_RAD_MIN_MIB=110000
|
||||
|
||||
@@ -1,9 +1,9 @@
|
||||
# frank-archon.service — radiance (StillDeadcode, Apache-2.0) endpoint
|
||||
# (OFFICIAL Qwen/Qwen3.8-Flash-Next-FP8 at NATIVE block-FP8 precision, the
|
||||
# rad-convert container qwen4exp-fp8-native.rad) on BOTH R9700s (TP=2,
|
||||
# wht6 wire), dankserver :7770. 2026-10-05 cutover from FreeToken (git tag
|
||||
# frank-archon-freetoken-pr587-20261005 is the pre-cutover state; the
|
||||
# retired unit/env/serve trio and Dockerfile are in that tag).
|
||||
# (the publisher's 4-bit-codebook container of the official
|
||||
# Qwen/Qwen3.8-Flash-Next, qwen3.8-next-flash-fp8-iq4r-moe.rad, fetched by
|
||||
# scripts/download-frank-archon-iq4r.sh) on BOTH R9700s (TP=2, wht6 wire),
|
||||
# dankserver :7770. 2026-10-15 payload swap from the in-house w4dn8 (the
|
||||
# swap commit is the revert; its .rad stays on disk).
|
||||
#
|
||||
# Same port, same served alias, same container identity as the unit name;
|
||||
# the harness models.yml id is unchanged. The serve script drives
|
||||
@@ -19,7 +19,7 @@
|
||||
# unit grants LimitMEMLOCK=infinity to the dank process via PID1; the
|
||||
# engine still runs out of dank's rootless podman storage.
|
||||
[Unit]
|
||||
Description=frank-archon — radiance Qwen3.8-Flash-Next-FP8 (native) on 2x R9700 TP=2
|
||||
Description=frank-archon — radiance Qwen3.8-Flash-Next (publisher iq4r) on 2x R9700 TP=2
|
||||
After=network-online.target
|
||||
Wants=network-online.target
|
||||
# Never let the start-rate limiter give up after a crash loop (a failed LLM
|
||||
|
||||
@@ -1,11 +1,13 @@
|
||||
#!/usr/bin/env bash
|
||||
# serve-frank-archon.sh — frank-archon endpoint: radiance (StillDeadcode,
|
||||
# Apache-2.0) serving the OFFICIAL Qwen/Qwen3.8-Flash-Next-FP8 checkpoint at
|
||||
# NATIVE block-FP8 precision from a rad-convert container
|
||||
# (/home/dank/models/rad/qwen4exp-fp8-native.rad), on BOTH R9700s (TP=2,
|
||||
# wht6 wire), dankserver :7770. 2026-10-05 cutover from FreeToken (PR #587,
|
||||
# one card; git tag frank-archon-freetoken-pr587-20261005 is the
|
||||
# pre-cutover state).
|
||||
# Apache-2.0) serving the PUBLISHER's 4-bit-codebook container of the
|
||||
# official Qwen/Qwen3.8-Flash-Next (the engine author's own rad-convert of
|
||||
# the bf16 checkpoint: qwen3.8-next-flash-fp8-iq4r-moe.rad, fetched by
|
||||
# scripts/download-frank-archon-iq4r.sh) on BOTH R9700s (TP=2, wht6 wire),
|
||||
# dankserver :7770. 2026-10-15 payload swap from the in-house w4dn8 of the
|
||||
# Swift1.5 finetune (payload on disk = rollback; the swap commit is the
|
||||
# revert); 2026-10-05 radiance cutover from FreeToken (git tag
|
||||
# frank-archon-freetoken-pr587-20261005 is the pre-radiance state).
|
||||
#
|
||||
# The run line below IS the engine argv: the image's entrypoint is the
|
||||
# engine and its tools sit beside it on PATH. Unlike every predecessor
|
||||
|
||||
@@ -366,13 +366,13 @@
|
||||
"model": {
|
||||
"unit": "archon",
|
||||
"role": "Frank's strongest and fastest model runtime",
|
||||
"hf": "https://huggingface.co/frank8465/Swift-1.5-Qwen3.8-Flash-Next-GPTQ-W4A8-Radiance-AMD-R9700",
|
||||
"hf": "https://huggingface.co/StillDeadcode/qwen3.8-next-flash-fp8-iq4r-moe",
|
||||
"tagline": "...Power Overwhelming...",
|
||||
"sfx": [
|
||||
"archon-power.ogg"
|
||||
],
|
||||
"equiv": "Equivalent to Claude Opus 4.8 / OpenAI-Terra (Summer 2026 frontier intelligence).",
|
||||
"spec": "Our own build: a GPTQ-w4 quant of Swift1.5-Qwen3.8-Flash-Next, quantized and tuned in-house (radiance, ~114 GiB) on twin AMD R9700s with more than 200 GB of system RAM — 200k-token context, three submissions at a time; sees images.",
|
||||
"spec": "The engine author's published quant: 4-bit codebook experts + int8 trunk of Qwen3.8-Flash-Next (radiance, ~114 GiB) on twin AMD R9700s with more than 200 GB of system RAM — 200k-token context, three submissions at a time; sees images.",
|
||||
"inputs": [
|
||||
"text",
|
||||
"image"
|
||||
|
||||
@@ -3,8 +3,10 @@
|
||||
#
|
||||
# This file asserts the RADIANCE shape (StillDeadcode engine, digest-pinned
|
||||
# stilldeadcode/radiance image, BOTH R9700s TP=2 on the wht6 wire, serving
|
||||
# the Swift1.5 Qwen3.8-Flash-Next GPTQ-w4 .rad built by
|
||||
# scripts/convert-swift15-w4dn8.sh). It replaces the FreeToken seam of
|
||||
# the publisher's 4-bit-codebook .rad of the official Qwen3.8-Flash-Next
|
||||
# (fetched by scripts/download-frank-archon-iq4r.sh; the in-house
|
||||
# Swift1.5 w4dn8 .rad of scripts/convert-swift15-w4dn8.sh is the on-disk
|
||||
# rollback). It replaces the FreeToken seam of
|
||||
# 2026-10-05 (git tag frank-archon-freetoken-pr587-20261005) and pins what
|
||||
# flags alone do not say: the served window clears the harness worst case,
|
||||
# the KV pool backs seqs x max-model-len at the declared cache dtype (an
|
||||
@@ -28,7 +30,7 @@ SERVE="$REPO_ROOT/scripts/serve-frank-archon.sh"
|
||||
TTM_LIB="$REPO_ROOT/scripts/ttm-preflight.sh"
|
||||
ENV_FILE="$REPO_ROOT/scripts/frank-archon.env"
|
||||
REMOTE_DEPLOY="$REPO_ROOT/scripts/deploy-remote.sh"
|
||||
DOWNLOAD="$REPO_ROOT/scripts/download-frank-archon-swift15.sh"
|
||||
DOWNLOAD="$REPO_ROOT/scripts/download-frank-archon-iq4r.sh"
|
||||
BUILD="$REPO_ROOT/scripts/convert-swift15-w4dn8.sh"
|
||||
HFGET="$REPO_ROOT/scripts/hfget.sh"
|
||||
TEMPLATE="$REPO_ROOT/scripts/qwen38-froggeric-v22.5.jinja"
|
||||
@@ -381,18 +383,23 @@ nosudo_bin() {
|
||||
grep -q 'exec podman wait "$FRANK_ARCHON_CONTAINER"' "$SERVE"
|
||||
}
|
||||
|
||||
@test "the model id matches the payload's build and fetch scripts" {
|
||||
# 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-archon-rad.sh +
|
||||
# download-frank-archon.sh.)
|
||||
@test "the model id matches the payload's fetch script (and the rollback's build script)" {
|
||||
# The deployed payload is the PUBLISHER's .rad: the fetch script names
|
||||
# the repo, the file, and the Hub's LFS sha256; nothing is converted on
|
||||
# the host for it. The in-house w4dn8 rollback keeps its own trio
|
||||
# (convert-swift15-w4dn8.sh + download-frank-archon-swift15.sh, and the
|
||||
# fp8-native era keeps build-frank-archon-rad.sh +
|
||||
# download-frank-archon.sh).
|
||||
grep -q '^FRANK_ARCHON_MODEL_DIR=/home/dank/models/rad$' "$ENV_FILE"
|
||||
grep -q '^FRANK_ARCHON_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 '^FRANK_ARCHON_MODEL_FILE=qwen3.8-next-flash-fp8-iq4r-moe.rad$' "$ENV_FILE"
|
||||
grep -q 'StillDeadcode/qwen3.8-next-flash-fp8-iq4r-moe' "$DOWNLOAD"
|
||||
grep -q 'qwen3.8-next-flash-fp8-iq4r-moe.rad' "$DOWNLOAD"
|
||||
grep -q '0af5e96244e80c21ac8edca1719dae49b8a201b94a2f3994c3e24026ceaa4d20' "$DOWNLOAD"
|
||||
grep -q 'hfget.sh' "$DOWNLOAD"
|
||||
# The repo is UNGATED — no token may be required on the fetch path.
|
||||
! grep -q 'HF_TOKEN' "$DOWNLOAD"
|
||||
# Rollback provenance: the w4dn8 build script names its payload.
|
||||
grep -q 'qwen4exp-swift15-w4dn8-i8-hc8m.rad' "$BUILD"
|
||||
}
|
||||
|
||||
@test "no bare HIP-reserved env var is defined" {
|
||||
|
||||
Reference in New Issue
Block a user