===== HOST ===== Hostname: ana-ml2 Date: 2026-04-19T22:15:48-07:00 Uptime: up 33 weeks, 1 day, 14 minutes OS: Debian GNU/Linux 13 (trixie) Kernel: 6.12.41+deb13-amd64 Arch: x86_64 ===== HARDWARE ===== CPU cores: 96 CPU model: AMD EPYC 9254 24-Core Processor MemTotal: 566.6 GB MemAvailable: 500.9 GB ===== GPUS ===== index, name, memory.total [MiB], memory.free [MiB], driver_version 0, NVIDIA RTX 6000 Ada Generation, 46068 MiB, 45456 MiB, 580.65.06 1, NVIDIA RTX 6000 Ada Generation, 46068 MiB, 34072 MiB, 580.65.06 ===== FILESYSTEMS (df) ===== Filesystem Size Used Avail Use% Mounted on zroot/ROOT/debian 434G 169G 265G 39% / efivarfs 128K 58K 66K 47% /sys/firmware/efi/efivars zroot/home 280G 15G 265G 6% /home /dev/sda1 511M 92M 420M 18% /boot/efi tank 8.6T 1.3T 7.3T 16% /tank ===== PERSISTENT MOUNTS (/etc/fstab, non-comment) ===== UUID="3D9B-8E0C" /boot/efi vfat defaults 0 0 ===== TARGETED DATA PATHS ===== /tank (total: 1.3T) 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 7 llmuser llm 8 2026-04-17 14:09 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 llmuser llm 12 2026-04-19 00:58 compose drwxrwxr-x 3 llmuser llmuser 3 2026-04-18 22:40 conf /opt/docker/compose (total: 110M) total 14 drwxrwxr-x 12 llmuser llm 12 2026-04-19 00:58 . drwxrwxr-x 4 lkraven lkraven 4 2025-09-03 20:19 .. drwxr-xr-x 2 root root 4 2026-04-19 00:58 beszel-agent drwxr-xr-x 2 llmuser llm 4 2025-09-05 20:36 comfyui drwxrwxr-x 2 llmuser llm 3 2025-09-03 17:23 dockge drwxr-xr-x 2 root root 4 2026-04-19 00:28 dozzle-agent drwxrwxr-x 3 llmuser llmuser 4 2026-04-11 23:17 kokoro drwxr-xr-x 2 llmuser llm 4 2025-09-03 17:34 llama-swap drwxr-xr-x 2 llmuser llm 4 2025-09-24 12:32 parakeet drwxr-xr-x 2 llmuser llmuser 2 2026-04-11 11:08 synapse drwxr-xr-x 2 llmuser llm 4 2025-09-10 18:03 vibevoice drwxr-xr-x 2 root root 4 2026-04-18 22:59 vllm-qwen3 /opt/docker/conf (total: 18K) total 2 drwxrwxr-x 3 llmuser llmuser 3 2026-04-18 22:40 . drwxrwxr-x 4 lkraven lkraven 4 2025-09-03 20:19 .. drwxrwxr-x 2 llmuser llmuser 4 2026-04-19 17:00 llama-swap /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: 6 (running 6, paused 0, stopped 0) Images: 39 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 beszel-agent henrygd/beszel-agent:latest Up 21 hours dozzle-agent amir20/dozzle:latest Up 22 hours 0.0.0.0:7007->7007/tcp, 8080/tcp llama-swap-llama-swap-1 ghcr.io/mostlygeek/llama-swap:cuda Up 5 hours (healthy) 0.0.0.0:9292->8080/tcp, [::]:9292->8080/tcp vllm-rerank vllm/vllm-openai:latest Up 23 hours (healthy) 0.0.0.0:8002->8000/tcp, [::]:8002->8000/tcp vllm-embed vllm/vllm-openai:latest Up 23 hours (healthy) 0.0.0.0:8001->8000/tcp, [::]:8001->8000/tcp dockge-dockge-1 louislam/dockge:latest Up 3 weeks (healthy) 0.0.0.0:5001->5001/tcp, [::]:5001->5001/tcp ----- all containers ----- NAMES IMAGE STATUS beszel-agent henrygd/beszel-agent:latest Up 21 hours dozzle-agent amir20/dozzle:latest Up 22 hours llama-swap-llama-swap-1 ghcr.io/mostlygeek/llama-swap:cuda Up 5 hours (healthy) vllm-rerank vllm/vllm-openai:latest Up 23 hours (healthy) vllm-embed vllm/vllm-openai:latest Up 23 hours (healthy) dockge-dockge-1 louislam/dockge:latest Up 3 weeks (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 88cea17a7577848d5a34a191ac1a01acb0cd196a2792cfdae6845053ede8b02b local beszel-agent_beszel_agent_data local ccb997d07399630358be058be83fe6f5ee64ca307f6dc03c669d9f137644b29a local dockge_dockge_data local dozzle-agent_dozzle_agent_data local librechat_pgdata2 local parakeet_parakeet_cache local searxng_searxng-data local ----- compose projects currently running ----- beszel-agent dockge dozzle-agent llama-swap vllm-qwen3 ===== COMPOSE FILES (/opt/docker/compose/) ===== >>> /opt/docker/compose/beszel-agent/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) # # 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: - ${BESZEL_PORT}:8090 volumes: - beszel_data:/beszel_data healthcheck: test: - CMD - wget - -qO- - http://localhost:8090/api/health interval: 30s timeout: 10s retries: 3 start_period: 15s networks: - tnet labels: - homepage.group=PFI-ANA - homepage.name=Beszel - homepage.icon=mdi-chart-line - homepage.description=Server + container monitoring - homepage.href=http://10.250.50.70:${BESZEL_PORT} beszel-agent: image: henrygd/beszel-agent:${BESZEL_VERSION} container_name: beszel-agent profiles: - agent restart: unless-stopped network_mode: host volumes: - /var/run/docker.sock:/var/run/docker.sock:ro - beszel_agent_data:/var/lib/beszel-agent environment: - PORT=${BESZEL_AGENT_PORT:-45876} - KEY=${BESZEL_HUB_KEY} - HUB_URL=${HUB_URL} - TOKEN=${BESZEL_TOKEN} - EXTRA_FILESYSTEMS=${BESZEL_EXTRA_FS:-} volumes: beszel_data: null beszel_agent_data: null 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 services: dockge: image: louislam/dockge:latest restart: unless-stopped ports: # Host Port : Container Port - 5001:5001 volumes: - /var/run/docker.sock:/var/run/docker.sock - dockge_data:/app/data - /opt/docker/compose:/opt/docker/compose labels: - homepage.group=PFI-ANA - homepage.name=Dockge-ML2 - homepage.icon=si-portainer - homepage.description=Docker - homepage.href=http://10.250.50.54:5001 environment: # Tell Dockge where is your stacks directory - DOCKGE_STACKS_DIR=/opt/docker/compose networks: - tnet volumes: dockge_data: null networks: tnet: name: traefik-net external: true >>> /opt/docker/compose/dozzle-agent/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=${DOZZLE_PASSWORD:-} healthcheck: test: ["CMD", "/dozzle", "healthcheck"] interval: 30s timeout: 10s retries: 3 start_period: 15s networks: - tnet labels: - homepage.group=PFI-ANA - homepage.name=Dozzle - homepage.icon=mdi-text-box-search - homepage.description=Container logs (ana-docker + ana-ml2) - homepage.href=http://10.250.50.70:${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 services: llama-swap: stdin_open: true tty: true runtime: nvidia volumes: - /opt/docker/conf/llama-swap/config.yaml:/app/config.yaml - /tank/aimodels/llm:/models - /tank/aimodels/huggingface:/hfcache environment: - HF_HOME=/hfcache - HF_HUB_CACHE=/hfcache/hub ports: - 9292:8080 image: ghcr.io/mostlygeek/llama-swap:cuda networks: - tnet 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/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-qwen3/compose.yaml # vLLM — Qwen3 Embedding + Reranker (one stack, two services). # # Replaces the unmaintained Infinity stack. vLLM runs one model per process, # so this stack brings up two 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 # # 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: # HF_HOME=/tank/aimodels/huggingface hf download Qwen/Qwen3-Embedding-0.6B # HF_HOME=/tank/aimodels/huggingface hf download Qwen/Qwen3-Reranker-0.6B 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 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.oldyaml /opt/docker/conf/llama-swap/config.yaml ===== LISTENING PORTS ===== 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 0.0.0.0:9292 [::]:22 *:2375 [::]:5001 [::]:8001 [::]:8002 [::]:9292 ===== MODEL / HUGGINGFACE CACHES ===== /tank/aimodels/huggingface (108G) hub entries: CACHEDIR.TAG datasets--HuggingFaceH4--ultrachat_200k datasets--mlabonne--harmful_behaviors datasets--mlabonne--harmless_alpaca 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--Skyfall-R1-31B-v4a-GGUF 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--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--newsletter--VibeVoice-Large-pt models--Qwen--Qwen2.5-0.5B-Instruct models--Qwen--Qwen3.6-35B-A3B models--Qwen--Qwen3-Embedding-0.6B models--Qwen--Qwen3-Omni-30B-A3B-Instruct models--Qwen--Qwen3-Reranker-0.6B models--Qwen--Qwen-Image-Edit-2509 models--unsloth--embeddinggemma-300m-GGUF models--unsloth--gemma-4-26B-A4B-it-GGUF models--unsloth--GLM-4.6-GGUF models--unsloth--GLM-4.7-Flash-GGUF models--unsloth--granite-4.0-h-micro-GGUF models--unsloth--granite-4.0-h-small-GGUF models--unsloth--granite-4.0-h-tiny-GGUF models--unsloth--Kimi-K2-Instruct-0905-GGUF /tank/aimodels/llm (790G) /home/lkraven/.cache/huggingface (2.1M) hub entries: 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--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 ===== DONE ===== Paste the above back into the chat, or pass a path as argv[1] to save.