
===== HOST =====

Hostname:   ana-ml2
Date:       2026-06-13T13:35:42-07:00
Uptime:     up 1 day, 6 minutes
OS:         Debian GNU/Linux 13 (trixie)
Kernel:     6.12.74+deb13+1-amd64
Arch:       x86_64

===== HARDWARE =====

CPU cores:  96
CPU model:  AMD EPYC 9254 24-Core Processor
MemTotal:   566.6 GB
MemAvailable: 484.5 GB

===== GPUS =====

index, name, memory.total [MiB], memory.free [MiB], driver_version
0, NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition, 97887 MiB, 97247 MiB, 580.65.06
1, NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition, 97887 MiB, 3692 MiB, 580.65.06

===== FILESYSTEMS (df) =====

Filesystem         Size  Used Avail Use% Mounted on
zroot/ROOT/debian  394G  212G  182G  54% /
efivarfs           128K   67K   57K  55% /sys/firmware/efi/efivars
/dev/sdb1          511M   92M  420M  18% /boot/efi
tank               8.6T  1.6T  7.1T  18% /tank
zroot/home         244G   62G  182G  26% /home

===== PERSISTENT MOUNTS (/etc/fstab, non-comment) =====

UUID="3D9B-8E0C" /boot/efi vfat defaults 0 0

===== TARGETED DATA PATHS =====

/tank  (total: 1.6T)
  total 15
  drwxrwxrwx  6 root    root     6 2026-04-11 23:17 .
  drwxr-xr-x 18 root    root    26 2026-03-29 16:08 ..
  drwxrwxr-x  9 llmuser llm     10 2026-06-12 18:01 aimodels
  drwxrwxr-x  3 llmuser llm      3 2025-09-08 13:21 comfy
  drwxrwxr-x  4 llmuser llmuser  4 2026-04-11 23:17 kokoro
  drwxrwxr-x  5 lkraven lkraven  6 2025-09-10 18:35 vibevoice

/opt  (total: 16G)
  total 79
  drwxrwxrwx 13 root    root    13 2026-04-17 23:00 .
  drwxr-xr-x 18 root    root    26 2026-03-29 16:08 ..
  drwx--x--x  4 root    root     4 2025-09-02 12:53 containerd
  drwxrwxr-x  4 lkraven lkraven  4 2025-09-03 20:19 docker
  drwxrwxr-x  8 llmuser llm     17 2026-04-17 17:50 heretic
  drwxrwxr-x 15 llmuser llmuser 36 2026-04-11 23:24 Kokoro-FastAPI
  drwxrwxr-x 20 llmuser llmuser 39 2025-10-09 21:42 LibreChat
  drwxrwxr-x 26 llmuser llmuser 56 2025-09-04 21:01 llama.cpp
  drwxrwxr-x 13 llmuser llmuser 25 2025-09-02 12:50 llama-swap
  drwxrwxr-x  3 llmuser llmuser 11 2026-04-18 15:48 llmcompressor
  drwxr-xr-x  4 root    root     4 2025-08-30 22:54 nvidia
  drwxrwxr-x  6 llmuser llmuser 15 2025-09-24 09:53 parakeet-tdt-0.6b-v2-fastapi
  drwxrwxr-x  2 llmuser llmuser  6 2025-09-05 10:03 uv

/opt/docker  (total: 110M)
  total 18
  drwxrwxr-x  4 lkraven lkraven  4 2025-09-03 20:19 .
  drwxrwxrwx 13 root    root    13 2026-04-17 23:00 ..
  drwxrwxr-x 12 lkraven lkraven 12 2026-06-13 02:32 compose
  drwxrwxr-x  4 lkraven lkraven  4 2026-06-04 00:26 conf

/opt/docker/compose  (total: 110M)
  total 30
  drwxrwxr-x 12 lkraven lkraven 12 2026-06-13 02:32 .
  drwxrwxr-x  4 lkraven lkraven  4 2025-09-03 20:19 ..
  drwxr-xr-x  2 lkraven lkraven  4 2026-04-20 18:47 beszel-agent-ana
  drwxr-xr-x  2 lkraven lkraven  4 2025-09-05 20:36 comfyui
  drwxr-xr-x  2 lkraven lkraven  4 2026-04-20 20:47 dockge
  drwxr-xr-x  2 lkraven lkraven  4 2026-04-20 20:44 dozzle-agent-ana
  drwxrwxr-x  3 lkraven lkraven  4 2026-04-11 23:17 kokoro
  drwxr-xr-x  2 lkraven lkraven  6 2026-06-12 15:17 llama-swap
  drwxr-xr-x  2 lkraven lkraven  4 2025-09-24 12:32 parakeet
  drwxrwxr-x  2 lkraven lkraven  4 2026-06-13 08:34 qwen35-vl
  drwxr-xr-x  2 lkraven lkraven  4 2025-09-10 18:03 vibevoice
  drwxr-xr-x  2 lkraven lkraven  9 2026-06-13 08:42 vllm

/opt/docker/conf  (total: 14K)
  total 2
  drwxrwxr-x 4 lkraven lkraven 4 2026-06-04 00:26 .
  drwxrwxr-x 4 lkraven lkraven 4 2025-09-03 20:19 ..
  drwxr-xr-x 2 lkraven lkraven 3 2026-06-05 00:22 llama-swap
  drwxr-xr-x 2 lkraven lkraven 2 2026-06-04 00:37 vllm

/var/lib/docker  (total: 8.5K)

/srv  (total: 512)
  total 9
  drwxr-xr-x  2 root root  2 2025-08-30 18:46 .
  drwxr-xr-x 18 root root 26 2026-03-29 16:08 ..


===== DOCKER =====

Server: 29.3.1   Client: 29.3.1

----- docker info -----
Containers:      9 (running 9, paused 0, stopped 0)
Images:          42
Runtimes:        map[io.containerd.runc.v2:{{runc []  map[]} map[org.opencontainers.runtime-spec.features:{"ociVersionMin":"1.0.0","ociVersionMax":"1.2.1","hooks":["prestart","createRuntime","createContainer","startContainer","poststart","poststop"],"mountOptions":["async","atime","bind","defaults","dev","diratime","dirsync","exec","iversion","lazytime","loud","mand","noatime","nodev","nodiratime","noexec","noiversion","nolazytime","nomand","norelatime","nostrictatime","nosuid","nosymfollow","private","ratime","rbind","rdev","rdiratime","relatime","remount","rexec","rnoatime","rnodev","rnodiratime","rnoexec","rnorelatime","rnostrictatime","rnosuid","rnosymfollow","ro","rprivate","rrelatime","rro","rrw","rshared","rslave","rstrictatime","rsuid","rsymfollow","runbindable","rw","shared","silent","slave","strictatime","suid","symfollow","sync","tmpcopyup","unbindable"],"linux":{"namespaces":["cgroup","ipc","mount","network","pid","time","user","uts"],"capabilities":["CAP_CHOWN","CAP_DAC_OVERRIDE","CAP_DAC_READ_SEARCH","CAP_FOWNER","CAP_FSETID","CAP_KILL","CAP_SETGID","CAP_SETUID","CAP_SETPCAP","CAP_LINUX_IMMUTABLE","CAP_NET_BIND_SERVICE","CAP_NET_BROADCAST","CAP_NET_ADMIN","CAP_NET_RAW","CAP_IPC_LOCK","CAP_IPC_OWNER","CAP_SYS_MODULE","CAP_SYS_RAWIO","CAP_SYS_CHROOT","CAP_SYS_PTRACE","CAP_SYS_PACCT","CAP_SYS_ADMIN","CAP_SYS_BOOT","CAP_SYS_NICE","CAP_SYS_RESOURCE","CAP_SYS_TIME","CAP_SYS_TTY_CONFIG","CAP_MKNOD","CAP_LEASE","CAP_AUDIT_WRITE","CAP_AUDIT_CONTROL","CAP_SETFCAP","CAP_MAC_OVERRIDE","CAP_MAC_ADMIN","CAP_SYSLOG","CAP_WAKE_ALARM","CAP_BLOCK_SUSPEND","CAP_AUDIT_READ","CAP_PERFMON","CAP_BPF","CAP_CHECKPOINT_RESTORE"],"cgroup":{"v1":true,"v2":true,"systemd":true,"systemdUser":true,"rdma":true},"seccomp":{"enabled":true,"actions":["SCMP_ACT_ALLOW","SCMP_ACT_ERRNO","SCMP_ACT_KILL","SCMP_ACT_KILL_PROCESS","SCMP_ACT_KILL_THREAD","SCMP_ACT_LOG","SCMP_ACT_NOTIFY","SCMP_ACT_TRACE","SCMP_ACT_TRAP"],"operators":["SCMP_CMP_EQ","SCMP_CMP_GE","SCMP_CMP_GT","SCMP_CMP_LE","SCMP_CMP_LT","SCMP_CMP_MASKED_EQ","SCMP_CMP_NE"],"archs":["SCMP_ARCH_AARCH64","SCMP_ARCH_ARM","SCMP_ARCH_MIPS","SCMP_ARCH_MIPS64","SCMP_ARCH_MIPS64N32","SCMP_ARCH_MIPSEL","SCMP_ARCH_MIPSEL64","SCMP_ARCH_MIPSEL64N32","SCMP_ARCH_PPC","SCMP_ARCH_PPC64","SCMP_ARCH_PPC64LE","SCMP_ARCH_RISCV64","SCMP_ARCH_S390","SCMP_ARCH_S390X","SCMP_ARCH_X32","SCMP_ARCH_X86","SCMP_ARCH_X86_64"],"knownFlags":["SECCOMP_FILTER_FLAG_TSYNC","SECCOMP_FILTER_FLAG_SPEC_ALLOW","SECCOMP_FILTER_FLAG_LOG"],"supportedFlags":["SECCOMP_FILTER_FLAG_TSYNC","SECCOMP_FILTER_FLAG_SPEC_ALLOW","SECCOMP_FILTER_FLAG_LOG"]},"apparmor":{"enabled":true},"selinux":{"enabled":true},"intelRdt":{"enabled":true},"mountExtensions":{"idmap":{"enabled":true}}},"annotations":{"io.github.seccomp.libseccomp.version":"2.6.0","org.opencontainers.runc.checkpoint.enabled":"true","org.opencontainers.runc.commit":"v1.3.4-0-gd6d73eb8","org.opencontainers.runc.version":"1.3.4\n"},"potentiallyUnsafeConfigAnnotations":["bundle","org.systemd.property.","org.criu.config"]}]} nvidia:{{nvidia-container-runtime []  map[]} map[org.opencontainers.runtime-spec.features:{"ociVersionMin":"1.0.0","ociVersionMax":"1.2.1","hooks":["prestart","createRuntime","createContainer","startContainer","poststart","poststop"],"mountOptions":["async","atime","bind","defaults","dev","diratime","dirsync","exec","iversion","lazytime","loud","mand","noatime","nodev","nodiratime","noexec","noiversion","nolazytime","nomand","norelatime","nostrictatime","nosuid","nosymfollow","private","ratime","rbind","rdev","rdiratime","relatime","remount","rexec","rnoatime","rnodev","rnodiratime","rnoexec","rnorelatime","rnostrictatime","rnosuid","rnosymfollow","ro","rprivate","rrelatime","rro","rrw","rshared","rslave","rstrictatime","rsuid","rsymfollow","runbindable","rw","shared","silent","slave","strictatime","suid","symfollow","sync","tmpcopyup","unbindable"],"linux":{"namespaces":["cgroup","ipc","mount","network","pid","time","user","uts"],"capabilities":["CAP_CHOWN","CAP_DAC_OVERRIDE","CAP_DAC_READ_SEARCH","CAP_FOWNER","CAP_FSETID","CAP_KILL","CAP_SETGID","CAP_SETUID","CAP_SETPCAP","CAP_LINUX_IMMUTABLE","CAP_NET_BIND_SERVICE","CAP_NET_BROADCAST","CAP_NET_ADMIN","CAP_NET_RAW","CAP_IPC_LOCK","CAP_IPC_OWNER","CAP_SYS_MODULE","CAP_SYS_RAWIO","CAP_SYS_CHROOT","CAP_SYS_PTRACE","CAP_SYS_PACCT","CAP_SYS_ADMIN","CAP_SYS_BOOT","CAP_SYS_NICE","CAP_SYS_RESOURCE","CAP_SYS_TIME","CAP_SYS_TTY_CONFIG","CAP_MKNOD","CAP_LEASE","CAP_AUDIT_WRITE","CAP_AUDIT_CONTROL","CAP_SETFCAP","CAP_MAC_OVERRIDE","CAP_MAC_ADMIN","CAP_SYSLOG","CAP_WAKE_ALARM","CAP_BLOCK_SUSPEND","CAP_AUDIT_READ","CAP_PERFMON","CAP_BPF","CAP_CHECKPOINT_RESTORE"],"cgroup":{"v1":true,"v2":true,"systemd":true,"systemdUser":true,"rdma":true},"seccomp":{"enabled":true,"actions":["SCMP_ACT_ALLOW","SCMP_ACT_ERRNO","SCMP_ACT_KILL","SCMP_ACT_KILL_PROCESS","SCMP_ACT_KILL_THREAD","SCMP_ACT_LOG","SCMP_ACT_NOTIFY","SCMP_ACT_TRACE","SCMP_ACT_TRAP"],"operators":["SCMP_CMP_EQ","SCMP_CMP_GE","SCMP_CMP_GT","SCMP_CMP_LE","SCMP_CMP_LT","SCMP_CMP_MASKED_EQ","SCMP_CMP_NE"],"archs":["SCMP_ARCH_AARCH64","SCMP_ARCH_ARM","SCMP_ARCH_MIPS","SCMP_ARCH_MIPS64","SCMP_ARCH_MIPS64N32","SCMP_ARCH_MIPSEL","SCMP_ARCH_MIPSEL64","SCMP_ARCH_MIPSEL64N32","SCMP_ARCH_PPC","SCMP_ARCH_PPC64","SCMP_ARCH_PPC64LE","SCMP_ARCH_RISCV64","SCMP_ARCH_S390","SCMP_ARCH_S390X","SCMP_ARCH_X32","SCMP_ARCH_X86","SCMP_ARCH_X86_64"],"knownFlags":["SECCOMP_FILTER_FLAG_TSYNC","SECCOMP_FILTER_FLAG_SPEC_ALLOW","SECCOMP_FILTER_FLAG_LOG"],"supportedFlags":["SECCOMP_FILTER_FLAG_TSYNC","SECCOMP_FILTER_FLAG_SPEC_ALLOW","SECCOMP_FILTER_FLAG_LOG"]},"apparmor":{"enabled":true},"selinux":{"enabled":true},"intelRdt":{"enabled":true},"mountExtensions":{"idmap":{"enabled":true}}},"annotations":{"io.github.seccomp.libseccomp.version":"2.6.0","org.opencontainers.runc.checkpoint.enabled":"true","org.opencontainers.runc.commit":"v1.3.4-0-gd6d73eb8","org.opencontainers.runc.version":"1.3.4\n"},"potentiallyUnsafeConfigAnnotations":["bundle","org.systemd.property.","org.criu.config"]}]} runc:{{runc []  map[]} map[org.opencontainers.runtime-spec.features:{"ociVersionMin":"1.0.0","ociVersionMax":"1.2.1","hooks":["prestart","createRuntime","createContainer","startContainer","poststart","poststop"],"mountOptions":["async","atime","bind","defaults","dev","diratime","dirsync","exec","iversion","lazytime","loud","mand","noatime","nodev","nodiratime","noexec","noiversion","nolazytime","nomand","norelatime","nostrictatime","nosuid","nosymfollow","private","ratime","rbind","rdev","rdiratime","relatime","remount","rexec","rnoatime","rnodev","rnodiratime","rnoexec","rnorelatime","rnostrictatime","rnosuid","rnosymfollow","ro","rprivate","rrelatime","rro","rrw","rshared","rslave","rstrictatime","rsuid","rsymfollow","runbindable","rw","shared","silent","slave","strictatime","suid","symfollow","sync","tmpcopyup","unbindable"],"linux":{"namespaces":["cgroup","ipc","mount","network","pid","time","user","uts"],"capabilities":["CAP_CHOWN","CAP_DAC_OVERRIDE","CAP_DAC_READ_SEARCH","CAP_FOWNER","CAP_FSETID","CAP_KILL","CAP_SETGID","CAP_SETUID","CAP_SETPCAP","CAP_LINUX_IMMUTABLE","CAP_NET_BIND_SERVICE","CAP_NET_BROADCAST","CAP_NET_ADMIN","CAP_NET_RAW","CAP_IPC_LOCK","CAP_IPC_OWNER","CAP_SYS_MODULE","CAP_SYS_RAWIO","CAP_SYS_CHROOT","CAP_SYS_PTRACE","CAP_SYS_PACCT","CAP_SYS_ADMIN","CAP_SYS_BOOT","CAP_SYS_NICE","CAP_SYS_RESOURCE","CAP_SYS_TIME","CAP_SYS_TTY_CONFIG","CAP_MKNOD","CAP_LEASE","CAP_AUDIT_WRITE","CAP_AUDIT_CONTROL","CAP_SETFCAP","CAP_MAC_OVERRIDE","CAP_MAC_ADMIN","CAP_SYSLOG","CAP_WAKE_ALARM","CAP_BLOCK_SUSPEND","CAP_AUDIT_READ","CAP_PERFMON","CAP_BPF","CAP_CHECKPOINT_RESTORE"],"cgroup":{"v1":true,"v2":true,"systemd":true,"systemdUser":true,"rdma":true},"seccomp":{"enabled":true,"actions":["SCMP_ACT_ALLOW","SCMP_ACT_ERRNO","SCMP_ACT_KILL","SCMP_ACT_KILL_PROCESS","SCMP_ACT_KILL_THREAD","SCMP_ACT_LOG","SCMP_ACT_NOTIFY","SCMP_ACT_TRACE","SCMP_ACT_TRAP"],"operators":["SCMP_CMP_EQ","SCMP_CMP_GE","SCMP_CMP_GT","SCMP_CMP_LE","SCMP_CMP_LT","SCMP_CMP_MASKED_EQ","SCMP_CMP_NE"],"archs":["SCMP_ARCH_AARCH64","SCMP_ARCH_ARM","SCMP_ARCH_MIPS","SCMP_ARCH_MIPS64","SCMP_ARCH_MIPS64N32","SCMP_ARCH_MIPSEL","SCMP_ARCH_MIPSEL64","SCMP_ARCH_MIPSEL64N32","SCMP_ARCH_PPC","SCMP_ARCH_PPC64","SCMP_ARCH_PPC64LE","SCMP_ARCH_RISCV64","SCMP_ARCH_S390","SCMP_ARCH_S390X","SCMP_ARCH_X32","SCMP_ARCH_X86","SCMP_ARCH_X86_64"],"knownFlags":["SECCOMP_FILTER_FLAG_TSYNC","SECCOMP_FILTER_FLAG_SPEC_ALLOW","SECCOMP_FILTER_FLAG_LOG"],"supportedFlags":["SECCOMP_FILTER_FLAG_TSYNC","SECCOMP_FILTER_FLAG_SPEC_ALLOW","SECCOMP_FILTER_FLAG_LOG"]},"apparmor":{"enabled":true},"selinux":{"enabled":true},"intelRdt":{"enabled":true},"mountExtensions":{"idmap":{"enabled":true}}},"annotations":{"io.github.seccomp.libseccomp.version":"2.6.0","org.opencontainers.runc.checkpoint.enabled":"true","org.opencontainers.runc.commit":"v1.3.4-0-gd6d73eb8","org.opencontainers.runc.version":"1.3.4\n"},"potentiallyUnsafeConfigAnnotations":["bundle","org.systemd.property.","org.criu.config"]}]}]
Default runtime: runc
Storage driver:  overlay2
Root dir:        /var/lib/docker
Server version:  29.3.1

----- running containers -----
NAMES          IMAGE                                STATUS                       PORTS
vllm-qwen35    vllm/vllm-openai                     Up About an hour (healthy)   0.0.0.0:8007->8000/tcp, [::]:8007->8000/tcp
vllm-granite   vllm/vllm-openai:latest              Up About an hour (healthy)   0.0.0.0:8004->8000/tcp, [::]:8004->8000/tcp
vllm-rerank    vllm/vllm-openai:latest              Up 13 hours (healthy)        0.0.0.0:8002->8000/tcp, [::]:8002->8000/tcp
vllm-embed     vllm/vllm-openai:latest              Up 13 hours (healthy)        0.0.0.0:8001->8000/tcp, [::]:8001->8000/tcp
vllm-reward    vllm/vllm-openai:latest              Up 13 hours (healthy)        0.0.0.0:8003->8000/tcp, [::]:8003->8000/tcp
llama-swap     ghcr.io/mostlygeek/llama-swap:cuda   Up 13 hours (healthy)        0.0.0.0:9292->8080/tcp, [::]:9292->8080/tcp
dockge         louislam/dockge:latest               Up 13 hours (healthy)        0.0.0.0:5001->5001/tcp, [::]:5001->5001/tcp
dozzle-agent   amir20/dozzle:latest                 Up 13 hours                  0.0.0.0:7007->7007/tcp, 8080/tcp
beszel-agent   henrygd/beszel-agent:latest          Up 13 hours (healthy)        

----- all containers -----
NAMES          IMAGE                                STATUS
vllm-qwen35    vllm/vllm-openai                     Up About an hour (healthy)
vllm-granite   vllm/vllm-openai:latest              Up About an hour (healthy)
vllm-rerank    vllm/vllm-openai:latest              Up 13 hours (healthy)
vllm-embed     vllm/vllm-openai:latest              Up 13 hours (healthy)
vllm-reward    vllm/vllm-openai:latest              Up 13 hours (healthy)
llama-swap     ghcr.io/mostlygeek/llama-swap:cuda   Up 13 hours (healthy)
dockge         louislam/dockge:latest               Up 13 hours (healthy)
dozzle-agent   amir20/dozzle:latest                 Up 13 hours
beszel-agent   henrygd/beszel-agent:latest          Up 13 hours (healthy)

----- networks -----
NAME                     DRIVER    SCOPE
bridge                   bridge    local
host                     host      local
kokoro-tts-gpu_default   bridge    local
librechat_default        bridge    local
llama-swap_default       bridge    local
none                     null      local
traefik-net              bridge    local

----- networks (external, non-default — worth knowing for compose external: true) -----
kokoro-tts-gpu_default
librechat_default
llama-swap_default
traefik-net

----- named volumes -----
VOLUME NAME                          DRIVER
beszel-agent-ana_beszel_agent_data   local
dockge_dockge_data                   local
dozzle-agent-ana_dozzle_agent_data   local
parakeet_parakeet_cache              local
searxng_searxng-data                 local

----- compose projects currently running -----
beszel-agent-ana
dockge
dozzle-agent-ana
llama-swap
qwen35-vl
vllm

===== COMPOSE FILES (/opt/docker/compose/) =====


>>> /opt/docker/compose/beszel-agent-ana/compose.yaml
# Beszel — lightweight server/container monitoring.
#
# Hub: single web UI with the SQLite store. Agents: per-host metric collectors
# that the hub pulls from over SSH.
#
# Multi-host layout via compose profiles:
#   COMPOSE_PROFILES=hub          → hub only        (ana-docker)
#   COMPOSE_PROFILES=hub,agent    → hub + local agent on the same host
#   COMPOSE_PROFILES=agent        → agent only      (ana-ml2, nh3-docker,
#                                                    esh-docker-vm, vm-esh-nas)
#
# The agent uses network_mode: host so it sees real host CPU/mem/net/disk
# counters rather than container-scoped ones — that's why it can't share
# the tnet network with the hub.
#
# All tunables live in .env — edit that, not this file.

services:
  beszel:
    image: henrygd/beszel:${BESZEL_VERSION}
    container_name: beszel
    profiles: [hub]
    restart: unless-stopped
    ports:
      - "${BESZEL_PORT}:8090"
    volumes:
      - beszel_data:/beszel_data
    healthcheck:
      # Hub image is distroless — no wget/curl. Use the bundled `/beszel`
      # binary's built-in health subcommand (https://beszel.dev/guide/healthchecks).
      test: ["CMD", "/beszel", "health", "--url", "http://localhost:8090"]
      interval: 120s
      timeout: 10s
      retries: 3
      start_period: 15s
    networks:
      - tnet
    labels:
      - homepage.group=Monitoring
      - homepage.name=Beszel
      - homepage.icon=mdi-chart-line
      - homepage.description=Server + container monitoring
      - homepage.href=http://10.250.50.70:${BESZEL_PORT}

  beszel-agent:
    image: henrygd/beszel-agent:${BESZEL_VERSION}
    container_name: beszel-agent
    profiles: [agent]
    restart: unless-stopped
    network_mode: host
    volumes:
      - /var/run/docker.sock:/var/run/docker.sock:ro
      - beszel_agent_data:/var/lib/beszel-agent
    environment:
      # Agent auth has two modes (v0.13+ supports both side-by-side):
      #   - KEY-mode: agent listens, hub connects inbound over SSH using KEY.
      #     Requires BESZEL_HUB_KEY in .env.
      #   - Token-mode: agent initiates an outbound connection to HUB_URL
      #     using TOKEN. Easier through NAT. Requires HUB_URL + BESZEL_TOKEN.
      # Leave unused ones empty ("") in .env; both can be set simultaneously.
      - PORT=${BESZEL_AGENT_PORT:-45876}
      - KEY=${BESZEL_HUB_KEY:-}
      - HUB_URL=${HUB_URL:-}
      - TOKEN=${BESZEL_TOKEN:-}
      - EXTRA_FILESYSTEMS=${BESZEL_EXTRA_FS:-}
    healthcheck:
      # Agent image ships the `/agent` binary with a `health` subcommand.
      # Verifies the agent process is up — not that the hub can reach it.
      test: ["CMD", "/agent", "health"]
      interval: 120s
      timeout: 10s
      retries: 3
      start_period: 15s

volumes:
  beszel_data:
  beszel_agent_data:

networks:
  tnet:
    name: traefik-net
    external: true

>>> /opt/docker/compose/comfyui/compose.yaml
services:
  comfyui:
    runtime: nvidia
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities:
                - gpu
                - compute
                - utility
    ports:
      - 8188:8188
    image: mmartial/comfyui-nvidia-docker:ubuntu24_cuda13.0-latest
    networks:
      - tnet
    volumes:
      - /tank/comfy/run:/comfy/mnt
      - /tank/aimodels/img/comfy:/basedir
    #user: 1001:1002
    environment:
      - WANTED_UID=1001
      - WANTED_GID=1002
      - BASE_DIRECTORY=/basedir
      - SECURITY_LEVEL=weak
      - NVIDIA_VISIBLE_DEVICES=all
      - NVIDIA_DRIVER_CAPABILITIES=all
    labels:
      - homepage.group=AI Systems
      - homepage.name=ComfyUI
      - homepage.icon=mdi-panorama-variant-outline
      - homepage.description=ComfyUI Image Gen (ana-ml2)
      - homepage.href=http://10.250.50.54:8188
    restart: unless-stopped
networks:
  tnet:
    name: traefik-net
    external: true

>>> /opt/docker/compose/dockge/compose.yaml
# Dockge — per-host Docker Compose UI (https://dockge.kuma.pet/).
#
# One instance runs on every Docker host so the compose dir is manageable
# from a browser. Each host sets DOCKGE_HOST_LABEL + DOCKGE_HOST_IP in its
# .env so the homepage card points at the right place.
#
# All tunables live in .env — edit that, not this file.

services:
  dockge:
    image: louislam/dockge:${DOCKGE_VERSION:-latest}
    container_name: dockge
    restart: unless-stopped
    ports:
      - "${DOCKGE_PORT:-5001}:5001"
    volumes:
      - /var/run/docker.sock:/var/run/docker.sock
      - dockge_data:/app/data
      - /opt/docker:/opt/docker
    environment:
      - DOCKGE_STACKS_DIR=/opt/docker/compose
    networks:
      - tnet
    labels:
      - homepage.group=Service Networking
      - homepage.name=Dockge (${DOCKGE_HOST_LABEL})
      - homepage.icon=sh-dockge.png
      - homepage.description=Compose UI on ${DOCKGE_HOST_LABEL}
      - homepage.href=http://${DOCKGE_HOST_IP}:${DOCKGE_PORT:-5001}

volumes:
  dockge_data:

networks:
  tnet:
    name: traefik-net
    external: true

>>> /opt/docker/compose/dozzle-agent-ana/compose.yaml
# Dozzle — container log viewer.
#
# Multi-host layout via compose profiles:
#   COMPOSE_PROFILES=hub   → runs the web UI (deploy on ana-docker)
#   COMPOSE_PROFILES=agent → runs the remote agent (deploy on ana-ml2)
#
# Same compose.yaml on both servers; per-host `.env` picks the profile.
#
# All tunables live in .env — edit that, not this file.

services:
  dozzle:
    image: amir20/dozzle:${DOZZLE_VERSION}
    container_name: dozzle
    profiles: [hub]
    restart: unless-stopped
    ports:
      - "${DOZZLE_PORT}:8080"
    volumes:
      - /var/run/docker.sock:/var/run/docker.sock:ro
      - dozzle_data:/data
    environment:
      - DOZZLE_HOSTNAME=${DOZZLE_HOSTNAME}
      - DOZZLE_REMOTE_AGENT=${DOZZLE_REMOTE_AGENT:-}
      - DOZZLE_AUTH_PROVIDER=${DOZZLE_AUTH_PROVIDER:-none}
      - DOZZLE_USERNAME=${DOZZLE_USERNAME:-}
      - DOZZLE_PASSWORD=${DOZZLE_PASSWORD:-}
    healthcheck:
      test: ["CMD", "/dozzle", "healthcheck"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 15s
    networks:
      - tnet
    labels:
      - homepage.group=Monitoring
      - homepage.name=Dozzle
      - homepage.icon=mdi-text-box-search
      - homepage.description=Container logs (ana-docker + ana-ml2)
      - homepage.href=http://10.250.50.70:${DOZZLE_PORT}

  dozzle-agent:
    image: amir20/dozzle:${DOZZLE_VERSION}
    container_name: dozzle-agent
    profiles: [agent]
    restart: unless-stopped
    command: agent
    ports:
      - "${DOZZLE_AGENT_BIND:-0.0.0.0}:${DOZZLE_AGENT_PORT}:7007"
    volumes:
      - /var/run/docker.sock:/var/run/docker.sock:ro
      - dozzle_agent_data:/data
    environment:
      - DOZZLE_HOSTNAME=${DOZZLE_HOSTNAME}
    networks:
      - tnet

volumes:
  dozzle_data:
  dozzle_agent_data:

networks:
  tnet:
    name: traefik-net
    external: true

>>> /opt/docker/compose/kokoro/compose.yaml
name: kokoro-tts
services:
  kokoro-tts:
    container_name: kokoro-tts
    build:
      context: ./Kokoro-FastAPI
      dockerfile: docker/gpu/Dockerfile
    volumes:
      - /tank/kokoro/models:/app/api/src/models
      - /tank/kokoro/output:/app/output
    ports:
      - "8765:8880"
    environment:
      - PYTHONPATH=/app:/app/api
      - USE_GPU=true
      - PYTHONUNBUFFERED=1
      - DOWNLOAD_MODEL=false
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]
    networks:
      - tnet
    labels:
      - homepage.group=AI Systems
      - homepage.name=Kokoro TTS
      - homepage.icon=mdi-waveform
      - homepage.description=Kokoro FastAPI TTS (OpenAI-compatible)
      - homepage.href=http://10.250.50.54:8765
    restart: unless-stopped

networks:
  tnet:
    name: traefik-net
    external: true


>>> /opt/docker/compose/llama-swap/compose.yaml
# llama-swap — GGUF model server with on-demand model swapping.
#
# Proxies OpenAI-compatible API requests to llama.cpp server instances
# and swaps which model is loaded into VRAM per request. Runs on
# ana-ml2 using both GPUs dynamically (no explicit device pinning —
# llama-swap picks per-model-definition).
#
# Model definitions live in /opt/docker/conf/llama-swap/config.yaml on
# the server. Canonical copy of that config is config.yaml in this
# workspace; deploy with scp + `docker compose restart` or the script
# at the bottom of README.md.
#
# All tunables live in .env — edit that, not this file.

services:
  llama-swap:
    image: ghcr.io/mostlygeek/llama-swap:${LLAMA_SWAP_VERSION}
    container_name: llama-swap
    restart: unless-stopped
    stdin_open: true
    tty: true
    runtime: nvidia
    ports:
      - "${LLAMA_SWAP_PORT}:8080"
    volumes:
      - /opt/docker/conf/llama-swap/config.yaml:/app/config.yaml
      - ${MODELS_DIR}:/models
      - ${HF_CACHE_DIR}:/hfcache
    environment:
      - HF_HOME=/hfcache
      - HF_HUB_CACHE=/hfcache/hub
      # Pin to GPU 0 — the reserved card for on-demand large-model hot-loads.
      # The always-on vLLM services (granite + embed/rerank/reward) own GPU 1;
      # keeping llama-swap off GPU 1 stops a hot-loaded model from contending
      # with them. llama.cpp then sees only GPU 0 (cuda:0), so --n-gpu-layers
      # 999 loads there with no per-model device targeting needed.
      - NVIDIA_VISIBLE_DEVICES=${LLAMA_SWAP_GPU:-0}
    healthcheck:
      test: ["CMD-SHELL", "curl -fsS http://localhost:8080/ >/dev/null || exit 1"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 30s
    networks:
      - tnet
    labels:
      - homepage.group=AI Systems
      - homepage.name=llama-swap
      - homepage.icon=mdi-swap-horizontal
      - homepage.description=GGUF model swapper (llama.cpp; ana-ml2)
      - homepage.href=http://10.250.50.54:${LLAMA_SWAP_PORT}

networks:
  tnet:
    name: traefik-net
    external: true

>>> /opt/docker/compose/parakeet/compose.yaml
services:
  parakeet-stt:
    image: parakeet-stt
    ports:
      - 8300:8000
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities:
                - gpu
    restart: unless-stopped
    volumes:
      - parakeet_cache:/root/.cache
    networks:
      - tnet
    env_file:
      - .env
    labels:
      - homepage.group=AI Systems
      - homepage.name=Parakeet
      - homepage.icon=mdi-talk
      - homepage.description=Parakeet STT (ana-ml2)
      - homepage.href=http://10.250.50.54:8300
networks:
  tnet:
    name: traefik-net
    external: true
volumes:
  parakeet_cache: null

>>> /opt/docker/compose/qwen35-vl/compose.yaml
# qwen35-vl — Qwen3.5-9B vision-language model (FP8) on ana-ml2.
#
# Co-located on GPU 1 with the granite summarizer + embed/rerank/reward trio
# (GPU 0 is deliberately kept free for hot-reloading large models). Serves on
# :8007, fronted by the LiteLLM gateway as `qwen3.5-9b-fp8`.
#
# WHY A PINNED NIGHTLY DIGEST (not :latest): vLLM :latest (v0.19.1) quantizes
# the Qwen3.5-VL *vision tower* under --quantization fp8, producing garbage
# vision output (the language model is unaffected — it answers text fine but
# "sees" noise). The nightly correctly excludes the vision tower, so vision
# works while the LM still gets the FP8 throughput/VRAM win. We pin the exact
# nightly digest for reproducibility — a moving :nightly tag would silently
# change the engine. WATCH: once the vision-FP8 exclusion lands in a stable
# release, re-pin to :latest and drop this note.
#
# WHY util 0.40 (not the trio's tiny values): the model needs ~34 GB just to
# start at 32k context (FP8 weights + BF16 vision tower + graph capture + 32k
# profiling). On shared GPU 1 (prod uses ~46 GB, ~48 GB free) this vLLM build
# requires free >= util*total, capping util at ~0.51 here; 0.40 (~38 GB) sits
# above the ~34 GB floor with ~10 GB card headroom.
#
# All tunables live in .env — edit that, not this file.

name: qwen35-vl

services:
  vllm-qwen35:
    image: ${QWEN_IMAGE}
    container_name: ${QWEN_CONTAINER_NAME}
    restart: unless-stopped
    ipc: host
    ports:
      - "${QWEN_PORT}:8000"
    volumes:
      - /tank/aimodels/huggingface:/hfcache
    environment:
      - HF_HOME=/hfcache
      - HF_HUB_CACHE=/hfcache/hub
      - HUGGING_FACE_HUB_TOKEN=${HF_TOKEN:-}
      - VLLM_API_KEY=${API_KEY:-}
    command:
      - ${QWEN_MODEL}
      - --served-model-name
      - ${QWEN_SERVED_NAME}
      - --quantization
      - fp8
      - --host
      - 0.0.0.0
      - --port
      - "8000"
      - --gpu-memory-utilization
      - ${QWEN_GPU_MEM_UTIL}
      - --max-model-len
      - ${QWEN_MAX_MODEL_LEN}
      - --dtype
      - auto
      # Prefix caching pinned ON (the nightly defaults it OFF). Free win for the
      # text-chat path; marginal for vision (each image is a distinct prefix).
      - --enable-prefix-caching
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              device_ids:
                - "${QWEN_GPU_ID}"
              capabilities:
                - gpu
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:8000/health"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 300s
    networks:
      - tnet
    labels:
      - homepage.group=AI Systems
      - homepage.name=Qwen3.5-9B VL (FP8)
      - homepage.icon=mdi-image-search
      - homepage.description=Qwen3.5-9B vision-language (FP8) via vLLM (ana-ml2)
      - homepage.href=http://10.250.50.54:${QWEN_PORT}/docs

networks:
  tnet:
    name: traefik-net
    external: true

>>> /opt/docker/compose/vibevoice/compose.yaml
services:
  vibevoice:
    container_name: vibevoice
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities:
                - gpu
    ports:
      - 8745:8745
    volumes:
      - /tank/vibevoice/hf:/root/.cache/huggingface
      - /tank/vibevoice/voices:/app/voices
      - /tank/vibevoice/state:/var/lib/eworker
    environment:
      - ENABLE_1_5B=true
      - ENABLE_LARGE=true
      - AUTH_REQUIRED=true
      - CORS_ENABLED=true
      - ALLOWED_ORIGINS=*
    image: eworkerinc/vibevoice:latest
    networks:
      - tnet
    labels:
      - homepage.group=AI Systems
      - homepage.name=VibeVoice
      - homepage.icon=mdi-chat
      - homepage.description=EWorkerStudio VibeVoice
      - homepage.href=http://10.250.50.54:8745
    restart: unless-stopped
networks:
  tnet:
    name: traefik-net
    external: true

>>> /opt/docker/compose/vllm/compose.yaml
# vLLM — Qwen3 Embedding + Reranker + Skywork Reward-V2 classifier.
#
# Originally created to replace the unmaintained Infinity stack (embed +
# rerank); generalized 2026-05-13 to host any vLLM-served model on ana-ml2,
# starting with the Skywork-Reward-V2-Llama-3.1-8B reward classifier
# (AWQ-quantized locally, served from /tank/aimodels/llm/).
#
# vLLM runs one model per process, so this stack brings up three containers
# sharing a single GPU:
#
#   vllm-embed   — Qwen3-Embedding served as an OpenAI /v1/embeddings server
#   vllm-rerank  — Qwen3-Reranker served as a /rerank + /score server
#   vllm-reward  — Skywork-Reward-V2-Llama-3.1-8B-AWQ served as a /classify scorer
#
# The reranker is a causal-LM checkpoint; --hf-overrides re-maps it to
# Qwen3ForSequenceClassification so vLLM's reranking endpoints work and the
# model only emits two class logits (no/yes) instead of the full 151k vocab.
#
# All tunables live in .env — edit that, not this file.
#
# Pre-download models to avoid first-run delay:
#   scripts/elway ana-ml2 --playbook playbooks/pull-hf-repo.yaml \
#       --var hf_repo=Qwen/Qwen3-Embedding-0.6B
#   scripts/elway ana-ml2 --playbook playbooks/pull-hf-repo.yaml \
#       --var hf_repo=Qwen/Qwen3-Reranker-0.6B
#
# Skywork-Reward-V2-Llama-3.1-8B-AWQ is a locally-quantized model — lives at
# /tank/aimodels/llm/Skywork-Reward-V2-Llama-3.1-8B-AWQ on ana-ml2 and is
# bind-mounted into the reward service at /local-models. Not from HF Hub.

services:
  vllm-embed:
    image: vllm/vllm-openai:${VLLM_VERSION}
    container_name: vllm-embed
    restart: unless-stopped
    ipc: host
    ports:
      - "${EMBED_PORT}:8000"
    volumes:
      - /tank/aimodels/huggingface:/hfcache
    environment:
      - HF_HOME=/hfcache
      - HF_HUB_CACHE=/hfcache/hub
      - HUGGING_FACE_HUB_TOKEN=${HF_TOKEN:-}
      - VLLM_API_KEY=${API_KEY:-}
    command:
      - ${EMBED_MODEL}
      - --served-model-name
      - ${EMBED_MODEL}
      - --runner
      - pooling
      - --host
      - 0.0.0.0
      - --port
      - "8000"
      - --gpu-memory-utilization
      - ${EMBED_GPU_MEM_UTIL}
      - --max-model-len
      - ${EMBED_MAX_MODEL_LEN}
      - --dtype
      - auto
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              device_ids:
                - "${GPU_ID}"
              capabilities:
                - gpu
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:8000/health"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 180s
    networks:
      - tnet
    labels:
      - homepage.group=AI Systems
      - homepage.name=vLLM Embed (Qwen3)
      - homepage.icon=mdi-vector-arrange-below
      - homepage.description=Qwen3 Embedding via vLLM (ana-ml2)
      - homepage.href=http://10.250.50.54:${EMBED_PORT}/docs

  vllm-rerank:
    image: vllm/vllm-openai:${VLLM_VERSION}
    container_name: vllm-rerank
    restart: unless-stopped
    ipc: host
    ports:
      - "${RERANK_PORT}:8000"
    volumes:
      - /tank/aimodels/huggingface:/hfcache
    environment:
      - HF_HOME=/hfcache
      - HF_HUB_CACHE=/hfcache/hub
      - HUGGING_FACE_HUB_TOKEN=${HF_TOKEN:-}
      - VLLM_API_KEY=${API_KEY:-}
    command:
      - ${RERANK_MODEL}
      - --served-model-name
      - ${RERANK_MODEL}
      - --runner
      - pooling
      - --hf-overrides
      - '{"architectures":["Qwen3ForSequenceClassification"],"classifier_from_token":["no","yes"],"is_original_qwen3_reranker":true}'
      - --host
      - 0.0.0.0
      - --port
      - "8000"
      - --gpu-memory-utilization
      - ${RERANK_GPU_MEM_UTIL}
      - --max-model-len
      - ${RERANK_MAX_MODEL_LEN}
      - --dtype
      - auto
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              device_ids:
                - "${GPU_ID}"
              capabilities:
                - gpu
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:8000/health"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 180s
    networks:
      - tnet
    labels:
      - homepage.group=AI Systems
      - homepage.name=vLLM Rerank (Qwen3)
      - homepage.icon=mdi-sort-variant
      - homepage.description=Qwen3 Reranker via vLLM (ana-ml2)
      - homepage.href=http://10.250.50.54:${RERANK_PORT}/docs

  vllm-reward:
    image: vllm/vllm-openai:${VLLM_VERSION}
    container_name: vllm-reward
    restart: unless-stopped
    ipc: host
    ports:
      - "${REWARD_PORT}:8000"
    volumes:
      # AWQ output lives in the legacy llama-swap models tree, not the HF cache
      # — bind-mount the LLM models dir read-only so the reward service can
      # load it as a local-path HF-format model.
      - /tank/aimodels/llm:/local-models:ro
    environment:
      - VLLM_API_KEY=${API_KEY:-}
    command:
      - /local-models/Skywork-Reward-V2-Llama-3.1-8B-AWQ
      - --served-model-name
      - Skywork/Skywork-Reward-V2-Llama-3.1-8B-AWQ
      # vLLM 0.19.1 deprecated --task in favor of --runner. The model's
      # config.json declares `LlamaForSequenceClassification` so the
      # pooling runner uses it as a classifier (single-label reward score)
      # without needing an explicit task flag.
      - --runner
      - pooling
      - --host
      - 0.0.0.0
      - --port
      - "8000"
      - --gpu-memory-utilization
      - ${REWARD_GPU_MEM_UTIL}
      - --max-model-len
      - ${REWARD_MAX_MODEL_LEN}
      - --dtype
      - auto
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              device_ids:
                - "${GPU_ID}"
              capabilities:
                - gpu
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:8000/health"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 240s
    networks:
      - tnet
    labels:
      - homepage.group=AI Systems
      - homepage.name=vLLM Reward (Skywork)
      - homepage.icon=mdi-scale-balance
      - homepage.description=Skywork-Reward-V2 8B classifier via vLLM (ana-ml2)
      - homepage.href=http://10.250.50.54:${REWARD_PORT}/docs

  # Phi-4-mini (FP8) — summarizer + "dreaming" agent. Supersedes the
  # llama-swap granite-4-small pin. Generative chat model (OpenAI
  # /v1/chat/completions), so NO --runner pooling. FP8 on RTX 6000 Ada
  # (cc 8.9): near-lossless, ~1.2x, ~6 GB.
  vllm-granite:
    image: vllm/vllm-openai:${VLLM_VERSION}
    container_name: vllm-granite
    restart: unless-stopped
    ipc: host
    ports:
      - "${GRANITE_PORT}:8000"
    volumes:
      - /tank/aimodels/huggingface:/hfcache
    environment:
      - HF_HOME=/hfcache
      - HF_HUB_CACHE=/hfcache/hub
      - HUGGING_FACE_HUB_TOKEN=${HF_TOKEN:-}
      - VLLM_API_KEY=${API_KEY:-}
    command:
      # Production summarizer (replaced phi4-mini 2026-06-05). Default = official
      # IBM pre-quantized FP8 (compressed-tensors), loaded directly; FP8 is native
      # on the RTX 6000 Ada (cc 8.9). Fallback to vLLM-native dynamic FP8 from
      # BF16: GRANITE_MODEL=ibm-granite/granite-4.1-8b + GRANITE_QUANT=fp8.
      - ${GRANITE_MODEL}
      - --served-model-name
      - ${GRANITE_SERVED_NAME}
      - --quantization
      - ${GRANITE_QUANT}
      - --host
      - 0.0.0.0
      - --port
      - "8000"
      - --gpu-memory-utilization
      - ${GRANITE_GPU_MEM_UTIL}
      - --max-model-len
      - ${GRANITE_MAX_MODEL_LEN}
      - --dtype
      - auto
      # CUDA graphs ENABLED (no --enforce-eager) for decode throughput. Made
      # room 2026-06-05 by right-sizing the embed/rerank/reward trio's KV pools
      # (they were over-provisioned at 5.9x/2.0x/3.9x concurrency); GPU 1 now has
      # ~17 GB free after granite, so graph-capture buffers fit. If the trio
      # ever grows back, granite may need --enforce-eager again on this card.
      # FP8 KV cache — halves KV memory; near-lossless on Ada (cc 8.9).
      - --kv-cache-dtype
      - ${GRANITE_KV_CACHE_DTYPE}
      # Prefix caching pinned EXPLICIT (vLLM v1 defaults it on, but pin so a
      # version flip can't silently disable it). Benched 2026-06-13: ~6.5x faster
      # TTFT (45ms vs 292ms) on a shared ~4.5k-token summarizer template; soft/
      # evictable KV, neutral when prefixes don't repeat — pure win for granite.
      - --enable-prefix-caching
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              device_ids:
                - "${GRANITE_GPU_ID}"
              capabilities:
                - gpu
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:8000/health"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 180s
    networks:
      - tnet
    labels:
      - homepage.group=AI Systems
      - homepage.name=vLLM Granite 4.1 8B (summarizer)
      - homepage.icon=mdi-text-box-outline
      - homepage.description=Granite 4.1 8B FP8 via vLLM (ana-ml2)
      - homepage.href=http://10.250.50.54:${GRANITE_PORT}/docs

networks:
  tnet:
    name: traefik-net
    external: true

===== CONFIG LAYOUT (/opt/docker/conf/ — top 200 entries) =====

/opt/docker/conf
/opt/docker/conf/llama-swap
/opt/docker/conf/llama-swap/config.yaml
/opt/docker/conf/vllm

===== LISTENING PORTS =====

0.0.0.0:111
0.0.0.0:22
0.0.0.0:5001
0.0.0.0:7007
0.0.0.0:8001
0.0.0.0:8002
0.0.0.0:8003
0.0.0.0:8004
0.0.0.0:8007
0.0.0.0:9292
[::]:111
[::]:22
*:2375
[::]:5001
[::]:8001
[::]:8002
[::]:8003
[::]:8004
[::]:8007
[::]:9292

===== MODEL / HUGGINGFACE CACHES =====

/tank/aimodels/huggingface  (342G)
  hub entries:
    CACHEDIR.TAG
    datasets--HuggingFaceH4--ultrachat_200k
    datasets--mlabonne--harmful_behaviors
    datasets--mlabonne--harmless_alpaca
    datasets--Skywork--Skywork-Reward-Preference-80K-v0.2
    datasets--wikitext
    models--AxionML--Qwen3.5-9B-NVFP4
    models--bartowski--Meta-Llama-3.1-8B-Instruct-GGUF
    models--bartowski--NousResearch_Hermes-4-14B-GGUF
    models--bartowski--TheDrummer_GLM-Steam-106B-A12B-v1-GGUF
    models--bartowski--TheDrummer_Skyfall-31B-v4-GGUF
    models--BeaverAI--Artemis-31B-v1i-GGUF
    models--BeaverAI--Skyfall-R1-31B-v4a-GGUF
    models--drawais--Granite-4.1-30B-NVFP4
    models--ibm-granite--granite-4.0-h-small-GGUF
    models--ibm-granite--granite-4.0-h-tiny-GGUF
    models--ibm-granite--granite-4.0-micro-GGUF
    models--ibm-granite--granite-4.1-8b
    models--ibm-granite--granite-4.1-8b-fp8
    models--llmfan46--Qwen3.6-35B-A3B-uncensored-heretic-GGUF
    models--microsoft--Phi-4-mini-instruct
    models--mradermacher--Daredevil-8B-abliterated-dpomix-GGUF
    models--mradermacher--Qwen3-30B-A3B-abliterated-erotic-i1-GGUF
    models--mradermacher--Qwen3.6-35B-A3B-abliterated-i1-GGUF
    models--mradermacher--Selene-1-Mini-Llama-3.1-8B-i1-GGUF
    models--murilonwt--granite-4.1-8b-NVFP4
    models--newsletter--VibeVoice-Large-pt
    models--Qwen--Qwen2.5-0.5B-Instruct
    models--Qwen--Qwen3.5-9B
    models--Qwen--Qwen3.6-35B-A3B

/tank/aimodels/llm  (794G)

/home/lkraven/.cache/huggingface  (15G)
  hub entries:
    CACHEDIR.TAG
    datasets--Salesforce--wikitext
    datasets--Skywork--Skywork-Reward-Preference-80K-v0.2
    datasets--wikitext
    models--Astralyra--bge-reranker-large-Q8_0-GGUF
    models--ggml-org--embeddinggemma-300M-GGUF
    models--ggml-org--Qwen3-Reranker-0.6B-Q8_0-GGUF
    models--jinaai--jina-reranker-v3-GGUF
    models--klnstpr--bge-reranker-v2-m3-Q8_0-GGUF
    models--minhtd14--jina-reranker-v2-base-multilingual-Q8_0-GGUF
    models--Mungert--Qwen3-Reranker-0.6B-GGUF
    models--Qwen--Qwen3-Embedding-0.6B-GGUF
    models--Qwen--Qwen3-Reranker-0.6B
    models--Skywork--Skywork-Reward-V2-Llama-3.1-8B
    models--unsloth--gemma-4-26B-A4B-it
    models--unsloth--gemma-4-26B-A4B-it-GGUF
    models--unsloth--gemma-4-31B-it-GGUF


===== DOCKER-ADJACENT SYSTEMD SERVICES =====

containerd.service running
docker.service running
nvidia-persistenced.service running

===== DONE =====

Paste the above back into the chat, or pass a path as argv[1] to save.
