Merge branch 'chore/fleet-image-refresh' into main

This commit is contained in:
Frank committed 2026-10-30 15:13:23 -07:00
commit 6ac544a7b6
6 files changed
+30 -21

No files matched your search

+1 -1
View File
@@ -21,7 +21,7 @@
# deployed knob has since dropped to 262144.
set -euo pipefail
IMG=ghcr.io/peonist-ai/halogen-flash-server@sha256:0c61bf84ac22308a53f5d1ca6b86806702d7039e5ebc51cae4c66621b92fe04a
IMG=ghcr.io/peonist-ai/halogen-flash-server@sha256:e35133b206da3094cc4d70c78800b26235bd9124b9aeb0e029d4a7c153b9cff0
CUR=/home/dank/models/halogen-flashnext-v2
NEW=/home/dank/models/halogen-v2-abliterated
CUR_CK=qwen38-flash-next-v2-swift15-abliterated.hgn
+1 -1
View File
@@ -1482,7 +1482,7 @@ deploy_anubis() {
# artifact would leave a restart-looping unit and a dark endpoint. The
# port gate is the same as every cutover since 2026-09-16: nothing
# starts until 7770 is released.
LLM_DRAGOON_IMAGE="${LLM_DRAGOON_IMAGE:-ghcr.io/peonist-ai/halogen-flash-server@sha256:0c61bf84ac22308a53f5d1ca6b86806702d7039e5ebc51cae4c66621b92fe04a}"
LLM_DRAGOON_IMAGE="${LLM_DRAGOON_IMAGE:-ghcr.io/peonist-ai/halogen-flash-server@sha256:e35133b206da3094cc4d70c78800b26235bd9124b9aeb0e029d4a7c153b9cff0}"
# The payload dir is its own twin because the NPU lane's containment gate below
# reads it; every artifact path under it stays a full literal as usual.
LLM_DRAGOON_MODEL_DIR="${LLM_DRAGOON_MODEL_DIR:-/home/dank/models/halogen-v2-abliterated}"
+21 -15
View File
@@ -8,8 +8,10 @@
# (/opt/halogen/npu/models.txt inside the image) and refuses to load a model
# whose files do not match.
#
# The manifest below IS that catalog block (dumped from the pinned 0.16.2
# image on 2026-10-19), so the files land in the layout the entrypoint
# The manifest below IS that catalog block (dumped from the pinned 0.18.20
# image on 2026-10-30; the 0.16.2 block this replaced named different device
# programs — 10 `u*.elf` and a 5,086,496 B consts.hnpb — so a version bump
# re-fetches the set or the entrypoint refuses the boot), so the files land in the layout the entrypoint
# expects — <dir>/<model-id>/devices/*, <dir>/<model-id>/<model-id>.hnpw and
# <dir>/<model-id>/tokenizer/tokenizer.json — and the endpoint can keep
# /models read-only and open no outbound connection at boot (HALOGEN_DOWNLOAD
@@ -57,21 +59,25 @@ manifest() {
case "$1" in
qwen3-embedding-0.6b)
NPU_REPO="peonist-ai/halogen-npu-qwen3-embedding-0.6b"
NPU_REV="4960fd9d4423dd15373ad21c83db48dbdb3b2798"
NPU_REV="8fd44c9f18861618a509bea75c51ff8a37e3bd5d"
FILES=(
"devices/NOTICE.md 3248 0f267b3d2523ddf14997ee58660a492a9eaf10ccf6b08bf19dfdc85b9a478b91"
"devices/consts.hnpb 5086496 ae430e41545a0b1012938cda373b0c450364d3be631111cca3a8c43679f93336"
"devices/devices.hnpm 24047 4e9bca9d95d084fb89ce5b99f579a00666c8ca1efae2613c53e3a4878cc9f174"
"devices/u0.elf 4931968 b38f165886cb037b7d3951d9cb878473eaba58a432acd45416ff85fd88aa4e46"
"devices/u1.elf 5456000 b1811feee851b8af833b37721da92099d89772110815bbbe2c3fa1c276f0ff42"
"devices/u2.elf 6505552 406ea9a95b470628a7382e376f4a72cdf4d7aa4c59b4ddf0a4bdd139d63d6ff2"
"devices/u3.elf 6817216 bc205d51b523d770151a0c61968f7c70bf624412827580bb6fe0aaf4650dc2ee"
"devices/u4.elf 7444032 a5a91338a2603acdcd5c11df532033fda2d3f5479ea44ae87f98fafbdff9a62d"
"devices/u5.elf 7432416 6c2bf41835569e0eba25ded7c05c7264ae69c6700bdeb4791057d884f2a4c126"
"devices/u6.elf 4941232 919d0038ca088eafddf195f3466ff38db27d3635be1cffa5d4d4b5140902a68e"
"devices/u7.elf 5488304 d904cf8afae9428dd167960549e18cce5441745f18c62f8c50975dffc077d3c2"
"devices/u8.elf 4941232 db3aef69b17825854ee0dd2df475125a3f5c872f95c686793d6af1ee83596fa7"
"devices/u9.elf 5488304 d182727e551084db8fb9600441d8aa373c7f09a3d267ae0a5e921ef92326db1c"
"devices/consts.hnpb 8495512 5af7c1f2f24d45a9054872bba882461cf7f6ffda832e785b700643d6467ad88b"
"devices/devices.hnpm 35465 85d870f6b900de1829659955f0dc701d57984580f5e5ec251add5d6969f03e3d"
"devices/u0.elf 2975008 f74df12eb8c79e4e90cbedcc1dd8f142219772d400e3a142fde8a95378b105eb"
"devices/u1.elf 3266848 ac5a3f89f934951b315b62ab53e1d0a74dbe6396134192641c405d08da332754"
"devices/u2.elf 4015328 5e4f0d3342f262816289866d7e8c966f56a9f938c2e12e7341718cc7312aa480"
"devices/u3.elf 4326976 94cf5d269fa286d91c26bf4654cedf101c047d23c4495b74c9c129cdc33b210f"
"devices/u4.elf 4953792 cbd2796050d4c675f5cb3da117111087d510173e26f262f1b36aab66dd49dc91"
"devices/u5.elf 4940112 7bf6a4470546bb888da02af395c07d92a24fb6d43aef27eb2151b3a9eda19e4d"
"devices/u6.elf 6174544 10b9d50b635993e1f9c23775c0b94901d922c1e433cd10910e9f97174235f5ac"
"devices/u7.elf 2983776 e0b06063b7379d05c85b3f435b819d96fda1223d8025d6d15958854b5711ace9"
"devices/u8.elf 3298656 3bad204f782a68b97e27c1172530b13d7fbb0b495fa95f9504530a1048560644"
"devices/u9.elf 2983776 875e313280358ce116e2a51a29a2c42794b5a9fadb3d48db702c90d18d838c2c"
"devices/u10.elf 3298656 ef2e0f399f149a5476955bcf233c6fa2e896fcef1f86ecb0d8113c952c41a8b2"
"devices/u11.elf 3298656 68a2519eee2d6a61ccc4ca2007e3186d44c9eb4e81162d742fe2f1756ec5a528"
"devices/u12.elf 3298656 2bdc6abfa58cac1d5795a3ef52fe8a9ab4e7c2a4792822d615499a913401f728"
"devices/u13.elf 3298656 4a3ce14f7ba15987b9bcbb4a010083e8aef68cd87c20cbe43403a98263179fe2"
"qwen3-embedding-0.6b.hnpw 813032248 b9f9901429df7b46ec17153aa3899f738adbea8e4356080da0c6e6586fb750d1"
"tokenizer/tokenizer.json 11423705 def76fb086971c7867b829c23a26261e38d9d74e02139253b38aeb9df8b4b50a"
) ;;
+5 -2
View File
@@ -10,8 +10,11 @@
# The .hgn format is the lock: it loads ONLY in the flash-server line, so the
# engine moves with the payload, never ahead of it.
# Image digest-pinned (a tag pull silently re-points; the digest is what was
# qualified — 0.16.2 is the version the model card names as its quickstart pin).
FRANK_DRAGOON_IMAGE=ghcr.io/peonist-ai/halogen-flash-server@sha256:0c61bf84ac22308a53f5d1ca6b86806702d7039e5ebc51cae4c66621b92fe04a
# qualified). 0.18.20 since 2026-10-30 (was 0.16.2, the model card's quickstart
# pin) — the vendor has moved two minor versions and the payload lock is what
# the deploy's health gate plus the boot ledger decide; rollback is the
# previous digest, 0c61bf84…, on this same line.
FRANK_DRAGOON_IMAGE=ghcr.io/peonist-ai/halogen-flash-server@sha256:e35133b206da3094cc4d70c78800b26235bd9124b9aeb0e029d4a7c153b9cff0
# Container identity kept from the 27B era: the unit's ExecStop names it.
FRANK_DRAGOON_CONTAINER=frank-dragoon-halogen
# Predecessor identity the serve script clears if it is still holding the GPUs.
+1 -1
View File
@@ -1,5 +1,5 @@
#!/usr/bin/env bash
# serve-frank-dragoon.sh — frank-dragoon endpoint: halogen-flash-server 0.16.2
# serve-frank-dragoon.sh — frank-dragoon endpoint: halogen-flash-server 0.18.20
# (closed-source engine, image ghcr.io/peonist-ai/halogen-flash-server,
# digest-pinned in frank-dragoon.env) serving Quat3rnion's NATIVE v2
# conversion (2026-10-11) of the abliterated Qwen3.8-Flash-Next on Dankclaw's
+1 -1
View File
@@ -1,7 +1,7 @@
#!/usr/bin/env bats
# Seam: frank-dragoon serves Quat3rnion's NATIVE v2 conversion (2026-10-11)
# of the abliterated Qwen3.8-Flash-Next (a .hgn flash-server payload) on the
# Strix Halo iGPU through the halogen-flash-server CONTAINER (0.16.2,
# Strix Halo iGPU through the halogen-flash-server CONTAINER (0.18.20,
# digest-pinned), driven by the root unit's serve script — 2 slots over ONE
# 401,408-position KV pool at the native 262,144 ceiling, MTP head always on (HALOGEN_SPEC_ADAPT=0)
# and the vision tower mounted. 2026-10-17 cutover from the Swift1.5-finetune