vh/esh-pfi-infrastructure
1
0
Fork 0
Code Issues 7 Pull Requests Actions Packages Projects Releases Wiki Activity
Files
6972e7ef7f0c8d15b9c750860db49bc5cc185b76
esh-pfi-infrastructure/stacks
T
History
vh 6972e7ef7f feat(erp-seat): run 7 quantized to NVFP4A16 and serving as the trial seat on ana-ml2 
- services/erp-seat-quant/run_quant_erp_v7.sh: v6 runner retargeted; dry-run gate
  passed identically (11,725 targets, 11,520 experts = 30x128x3, routers+vision BF16)
- 49 GiB bf16 relayed gx10 -> ana-ml2 (no key path either way; nh3-dev relays),
  checksums verified against source; quant 49 -> 16 GiB, all post-steps clean
- stacks/erp-seat: .env-driven swap to erp-tune-v7-nvfp4a16, served under its TRUE
  name; homepage labels + README updated, v6 rollback path recorded
- stacks/litellm: trial -> erp-tune-v7-nvfp4a16 (config-file alias; /model/update
  refuses a config model, so this is an edit + restart)
2026-09-09 15:30:15 -07:00
..
ace-step
chore(fleet): repoint stale irv-ml1 refs (10.100.79.3 -> irv-ml1.nh3.internal)
2026-09-07 15:08:56 -07:00
adguard-ana
feat(homepage): recategorise on "do I open this?", collapse the API groups
2026-08-24 08:54:06 -07:00
althing-chamber
althing-chamber: add valkey for Phase 3.1 cross-process streaming
2026-05-17 08:36:46 -07:00
althing-post-office
deploy(althing): post office to 3.6.0 — handle delete/retire verbs go live
2026-09-05 09:40:19 -07:00
ana-ml2-proxy
feat(homepage): wire ana-ml2 back into discovery via socat proxy on ana-docker
2026-09-07 16:34:13 -07:00
arbo
chore(fleet): repoint stale irv-ml1 refs (10.100.79.3 -> irv-ml1.nh3.internal)
2026-09-07 15:08:56 -07:00
asset-engine
chore(fleet): repoint stale irv-ml1 refs (10.100.79.3 -> irv-ml1.nh3.internal)
2026-09-07 15:08:56 -07:00
backrest
homepage: function-first layout + fleet label sweep
2026-04-20 22:14:00 -07:00
beszel
corviduo-dev: deploy beszel + dozzle monitoring agents
2026-05-23 18:13:59 -07:00
calibre-web-automated
calibre-web-automated: fix healthcheck (curl, not wget)
2026-04-20 22:28:30 -07:00
char-rp-gguf
feat(gpu): relocate char-rp to GPU1 + re-optimize both ana-ml2 cards for max context
2026-07-16 09:28:07 -07:00
chatterbox
chore(fleet): repoint stale irv-ml1 refs (10.100.79.3 -> irv-ml1.nh3.internal)
2026-09-07 15:08:56 -07:00
chatterbox-fast
refactor: extract chatterbox-fast to its own repo (vh/chatterbox-fast)
2026-06-02 10:52:04 -07:00
comfyui
chore(fleet): repoint stale irv-ml1 refs (10.100.79.3 -> irv-ml1.nh3.internal)
2026-09-07 15:08:56 -07:00
cosyvoice
chore(fleet): repoint stale irv-ml1 refs (10.100.79.3 -> irv-ml1.nh3.internal)
2026-09-07 15:08:56 -07:00
darkscarlett-charrp-reasoning
stacks(char-rp): compose-ify the two NVFP4 RP seats (MeroMero + Dark-Scarlett)
2026-08-12 11:15:33 -07:00
dia
chore(fleet): repoint stale irv-ml1 refs (10.100.79.3 -> irv-ml1.nh3.internal)
2026-09-07 15:08:56 -07:00
dockge
feat(homepage): recategorise on "do I open this?", collapse the API groups
2026-08-24 08:54:06 -07:00
dots-tts
refactor(dots-tts): extract TTS stack to tts-stack repo; pointer stub + move voices out
2026-08-11 07:46:11 -07:00
dozzle
corviduo-dev: deploy beszel + dozzle monitoring agents
2026-05-23 18:13:59 -07:00
erp-seat
feat(erp-seat): run 7 quantized to NVFP4A16 and serving as the trial seat on ana-ml2
2026-09-09 15:30:15 -07:00
fablefusion-charrp-probe
feat(refusal-probe): A/B refusal harness + Fable-Fusion 711 probe seat
2026-08-15 23:14:05 -07:00
filezilla
fix(filezilla): set restart: unless-stopped and canonicalize the stack
2026-08-22 09:50:51 -07:00
fish-s2
chore(fleet): repoint stale irv-ml1 refs (10.100.79.3 -> irv-ml1.nh3.internal)
2026-09-07 15:08:56 -07:00
gateway-chat
fix(gateway-chat): guard max_tokens against NaN from an empty field
2026-08-16 15:15:02 -07:00
gemma4-charrp
docs(gemma4-charrp): abliteration measured in isolation — close to free, but it MOVES capability
2026-08-24 15:39:43 -07:00
gemma4-trainee-bench
feat(gemma4-trainee-bench): BF16 bench stack; record that gen's footprint grows with uptime
2026-08-24 14:19:49 -07:00
gen-seat
fix(gen-seat): AEON W4A4 was the defect — purged; mixed FP8-attn build is primary gen
2026-08-17 00:59:50 -07:00
gitea-runner
docs(gitea-runner): state that a runs-on label list is AND, not fallback
2026-09-02 09:26:19 -07:00
heretic2-charrp-reasoning
feat(heretic2-charrp-reasoning): track the NVFP4+MTP reasoning seat
2026-08-18 23:53:59 -07:00
homepage
feat(homepage): wire ana-ml2 back into discovery via socat proxy on ana-docker
2026-09-07 16:34:13 -07:00
hrafn
docs(hrafn-ci): mirror the now-canonical vh/hrafn pipeline; record two failed runs
2026-08-23 02:55:02 -07:00
index-tts
chore(fleet): repoint stale irv-ml1 refs (10.100.79.3 -> irv-ml1.nh3.internal)
2026-09-07 15:08:56 -07:00
kokoro
chore(fleet): repoint stale irv-ml1 refs (10.100.79.3 -> irv-ml1.nh3.internal)
2026-09-07 15:08:56 -07:00
kyutai-tts
chore(fleet): repoint stale irv-ml1 refs (10.100.79.3 -> irv-ml1.nh3.internal)
2026-09-07 15:08:56 -07:00
langfuse
feat(langfuse): stand up Langfuse v3 + wire the LiteLLM trace callback
2026-06-05 11:35:01 -07:00
litellm
feat(erp-seat): run 7 quantized to NVFP4A16 and serving as the trial seat on ana-ml2
2026-09-09 15:30:15 -07:00
llama-swap
feat(ana-ml2): replace Qwen3.5-9B vision with Qwen3.6-35B-A3B FP8 on GPU 1
2026-06-14 14:41:49 -07:00
lobe-chat
feat(homepage): recategorise on "do I open this?", collapse the API groups
2026-08-24 08:54:06 -07:00
memos
feat(homepage): recategorise on "do I open this?", collapse the API groups
2026-08-24 08:54:06 -07:00
meromero-charrp
feat(gemma4-trainee-bench): BF16 bench stack; record that gen's footprint grows with uptime
2026-08-24 14:19:49 -07:00
mimir-inbox
feat(mimir-inbox): book-ingestion UI stack on corviduo-dev:8091 (#377)
2026-08-01 14:31:14 -07:00
miniflux
feat(homepage): recategorise on "do I open this?", collapse the API groups
2026-08-24 08:54:06 -07:00
mistral-small-4
feat(selene+mistral): restore Selene judge (FP8, GPU1) + push Mistral to 256K
2026-06-15 18:52:26 -07:00
mistral-small-4-heretic
feat(stacks): mistral-small-4-heretic drop-in (abliterated NVFP4 backend swap)
2026-06-17 22:33:29 -07:00
mog-sec
feat: althing v3.0.0 cutover (U9b) and the sec seat onto GPU0
2026-08-28 07:19:18 -07:00
mOrpheus
chore(fleet): repoint stale irv-ml1 refs (10.100.79.3 -> irv-ml1.nh3.internal)
2026-09-07 15:08:56 -07:00
muninn-gate
docs(muninn-gate): Dockerfile comment — dispatch pin now 0.1.5, SHA-tag note
2026-08-01 17:27:14 -07:00
omnivoice
chore(fleet): repoint stale irv-ml1 refs (10.100.79.3 -> irv-ml1.nh3.internal)
2026-09-07 15:08:56 -07:00
open-webui
chore(fleet): repoint stale irv-ml1 refs (10.100.79.3 -> irv-ml1.nh3.internal)
2026-09-07 15:08:56 -07:00
parakeet
chore(fleet): repoint stale irv-ml1 refs (10.100.79.3 -> irv-ml1.nh3.internal)
2026-09-07 15:08:56 -07:00
park
docs(park): record the API-key ruling — leave it as is
2026-08-18 05:49:10 -07:00
phasefinal-web
feat(phasefinal-web): cloudflare edge config — cache ruleset + always online
2026-08-29 23:02:49 -07:00
qwen3-tts
chore(fleet): repoint stale irv-ml1 refs (10.100.79.3 -> irv-ml1.nh3.internal)
2026-09-07 15:08:56 -07:00
qwen3.5-122b
fix(qwen3.5-122b): enable tool-calling (--enable-auto-tool-choice --tool-call-parser qwen3_xml)
2026-06-19 01:56:56 -07:00
qwen36-vl
tune(gpu1): grow selene 0.13→0.17 + qwen36 0.32→0.34 into the buffer
2026-06-15 20:36:04 -07:00
qwen-image-bench
feat(homepage): split AI fleet into role-based groups on a dedicated AI tab
2026-07-14 20:05:50 -07:00
qwopus3.5-122b
feat(homepage): split AI fleet into role-based groups on a dedicated AI tab
2026-07-14 20:05:50 -07:00
rest-server-ana
feat(homepage): recategorise on "do I open this?", collapse the API groups
2026-08-24 08:54:06 -07:00
rest-server-nh3
homepage: function-first layout + fleet label sweep
2026-04-20 22:14:00 -07:00
scriberr
feat(homepage): recategorise on "do I open this?", collapse the API groups
2026-08-24 08:54:06 -07:00
seafile
fix(searxng,seafile): repair wget healthcheck argv, restore seafile after 3-month outage
2026-08-18 22:27:15 -07:00
searxng
feat(searxng): move to nh3-docker, update, and expose as an MCP tool
2026-09-03 14:07:06 -07:00
selene
feat(selene): retire the seat; chat-judge -> gen, selene-1-mini-8b 404s by design
2026-08-23 05:07:01 -07:00
sglang
feat(sglang): stage vLLM-vs-SGLang bench stack on ana-ml2
2026-06-12 22:40:26 -07:00
skaldsong
chore(fleet): repoint stale irv-ml1 refs (10.100.79.3 -> irv-ml1.nh3.internal)
2026-09-07 15:08:56 -07:00
speaches
chore(fleet): repoint stale irv-ml1 refs (10.100.79.3 -> irv-ml1.nh3.internal)
2026-09-07 15:08:56 -07:00
stable-audio-open
chore(fleet): repoint stale irv-ml1 refs (10.100.79.3 -> irv-ml1.nh3.internal)
2026-09-07 15:08:56 -07:00
synapse
feat(synapse): restrict /_synapse/admin to LAN, track the stack
2026-09-01 16:09:42 -07:00
task-board
ci/task-board: drop explicit container, inherit runner default
2026-04-29 18:49:35 -07:00
uptimekuma
fix(homepage): pin UltraSeedbox to one tab, dedupe Uptime Kuma, size columns to members
2026-08-18 19:12:02 -07:00
vibevoice
chore(fleet): repoint stale irv-ml1 refs (10.100.79.3 -> irv-ml1.nh3.internal)
2026-09-07 15:08:56 -07:00
vllm
fix(nevermore): repoint onto live aliases — its LLM pass had been dead 8 days
2026-08-20 23:50:53 -07:00
vor
vor: pass VOR_WORLDTREE_KEY through to the container
2026-05-12 00:00:31 -07:00
voxtral
chore(fleet): repoint stale irv-ml1 refs (10.100.79.3 -> irv-ml1.nh3.internal)
2026-09-07 15:08:56 -07:00
waterland-studio
chore(fleet): repoint stale irv-ml1 refs (10.100.79.3 -> irv-ml1.nh3.internal)
2026-09-07 15:08:56 -07:00
wgtunnel
stacks(wgtunnel): mirror deployed wstunnel server stack from ana-docker
2026-08-12 10:01:46 -07:00
zed-fim-proxy
feat(homepage): recategorise on "do I open this?", collapse the API groups
2026-08-24 08:54:06 -07:00
zonos
chore(fleet): repoint stale irv-ml1 refs (10.100.79.3 -> irv-ml1.nh3.internal)
2026-09-07 15:08:56 -07:00
zonos-engine
docs(zonos-engine): capture the production ZONOS2 :1920 launch config (was live-only)
2026-07-17 09:03:05 -07:00
zonos-gateway
chore(fleet): repoint stale irv-ml1 refs (10.100.79.3 -> irv-ml1.nh3.internal)
2026-09-07 15:08:56 -07:00