===== HOST ===== Hostname: esh-ml1.esteban.net Date: 2026-09-25T05:35:31+00:00 Uptime: up 20 minutes OS: Debian GNU/Linux 12 (bookworm) Kernel: 6.8.12-42-pve Arch: x86_64 ===== HARDWARE ===== CPU cores: 6 CPU model: 13th Gen Intel(R) Core(TM) i9-13900H MemTotal: 16.0 GB MemAvailable: 9.8 GB ===== GPUS ===== index, name, memory.total [MiB], memory.free [MiB], driver_version 0, NVIDIA RTX 2000E Ada Generation, 16380 MiB, 11072 MiB, 580.178.04 ===== FILESYSTEMS (df) ===== Filesystem Size Used Avail Use% Mounted on /dev/mapper/pve-vm--110--disk--0 79G 34G 41G 45% / ===== PERSISTENT MOUNTS (/etc/fstab, non-comment) ===== ===== TARGETED DATA PATHS ===== /opt (total: 3.3G) total 20 drwxr-xr-x 5 root root 4096 2026-09-25 05:16 . drwxr-xr-x 18 root root 4096 2026-09-25 05:14 .. drwxrwsr-x 3 root docker 4096 2026-09-25 05:16 aimodels drwx--x--x 4 root root 4096 2026-09-25 05:15 containerd drwxrwsr-x 4 root docker 4096 2026-09-25 05:15 docker /opt/docker (total: 32K) total 16 drwxrwsr-x 4 root docker 4096 2026-09-25 05:15 . drwxr-xr-x 5 root root 4096 2026-09-25 05:16 .. drwxrwsr-x 3 root docker 4096 2026-09-25 05:16 compose drwxrwsr-x 2 root docker 4096 2026-09-25 05:15 conf /opt/docker/compose (total: 24K) total 12 drwxrwsr-x 3 root docker 4096 2026-09-25 05:16 . drwxrwsr-x 4 root docker 4096 2026-09-25 05:15 .. drwxrwsr-x 2 root docker 4096 2026-09-25 05:17 embed-rerank /opt/docker/conf (total: 4.0K) total 8 drwxrwsr-x 2 root docker 4096 2026-09-25 05:15 . drwxrwsr-x 4 root docker 4096 2026-09-25 05:15 .. /var/lib/docker (total: 4.0K) /srv (total: 4.0K) total 8 drwxr-xr-x 2 root root 4096 2025-09-07 15:14 . drwxr-xr-x 18 root root 4096 2026-09-25 05:14 .. ===== DOCKER ===== Server: 29.8.1 Client: 29.8.1 ----- docker info ----- Containers: 2 (running 2, paused 0, stopped 0) Images: 2 Runtimes: map[io.containerd.runc.v2:{{runc [] map[]} map[org.opencontainers.runtime-spec.features:{"ociVersionMin":"1.0.0","ociVersionMax":"1.3.0","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_LOONGARCH64","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","SECCOMP_FILTER_FLAG_WAIT_KILLABLE_RECV"],"supportedFlags":["SECCOMP_FILTER_FLAG_TSYNC","SECCOMP_FILTER_FLAG_SPEC_ALLOW","SECCOMP_FILTER_FLAG_LOG"]},"apparmor":{"enabled":true},"selinux":{"enabled":true},"intelRdt":{"enabled":true,"schemata":true,"monitoring":true},"memoryPolicy":{"modes":["MPOL_BIND","MPOL_DEFAULT","MPOL_INTERLEAVE","MPOL_LOCAL","MPOL_PREFERRED","MPOL_PREFERRED_MANY","MPOL_WEIGHTED_INTERLEAVE"],"flags":["MPOL_F_NUMA_BALANCING","MPOL_F_RELATIVE_NODES","MPOL_F_STATIC_NODES"]},"mountExtensions":{"idmap":{"enabled":true}},"netDevices":{"enabled":true}},"annotations":{"io.github.seccomp.libseccomp.version":"2.5.4","org.opencontainers.runc.checkpoint.enabled":"true","org.opencontainers.runc.commit":"v1.5.1-0-g8f2685a4","org.opencontainers.runc.version":"1.5.1"},"potentiallyUnsafeConfigAnnotations":["bundle","org.systemd.property.","org.criu.config"]}]} nvidia:{{nvidia-container-runtime [] map[]} map[org.opencontainers.runtime-spec.features:{"ociVersionMin":"1.0.0","ociVersionMax":"1.3.0","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_LOONGARCH64","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","SECCOMP_FILTER_FLAG_WAIT_KILLABLE_RECV"],"supportedFlags":["SECCOMP_FILTER_FLAG_TSYNC","SECCOMP_FILTER_FLAG_SPEC_ALLOW","SECCOMP_FILTER_FLAG_LOG"]},"apparmor":{"enabled":true},"selinux":{"enabled":true},"intelRdt":{"enabled":true,"schemata":true,"monitoring":true},"memoryPolicy":{"modes":["MPOL_BIND","MPOL_DEFAULT","MPOL_INTERLEAVE","MPOL_LOCAL","MPOL_PREFERRED","MPOL_PREFERRED_MANY","MPOL_WEIGHTED_INTERLEAVE"],"flags":["MPOL_F_NUMA_BALANCING","MPOL_F_RELATIVE_NODES","MPOL_F_STATIC_NODES"]},"mountExtensions":{"idmap":{"enabled":true}},"netDevices":{"enabled":true}},"annotations":{"io.github.seccomp.libseccomp.version":"2.5.4","org.opencontainers.runc.checkpoint.enabled":"true","org.opencontainers.runc.commit":"v1.5.1-0-g8f2685a4","org.opencontainers.runc.version":"1.5.1"},"potentiallyUnsafeConfigAnnotations":["bundle","org.systemd.property.","org.criu.config"]}]} runc:{{runc [] map[]} map[org.opencontainers.runtime-spec.features:{"ociVersionMin":"1.0.0","ociVersionMax":"1.3.0","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_LOONGARCH64","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","SECCOMP_FILTER_FLAG_WAIT_KILLABLE_RECV"],"supportedFlags":["SECCOMP_FILTER_FLAG_TSYNC","SECCOMP_FILTER_FLAG_SPEC_ALLOW","SECCOMP_FILTER_FLAG_LOG"]},"apparmor":{"enabled":true},"selinux":{"enabled":true},"intelRdt":{"enabled":true,"schemata":true,"monitoring":true},"memoryPolicy":{"modes":["MPOL_BIND","MPOL_DEFAULT","MPOL_INTERLEAVE","MPOL_LOCAL","MPOL_PREFERRED","MPOL_PREFERRED_MANY","MPOL_WEIGHTED_INTERLEAVE"],"flags":["MPOL_F_NUMA_BALANCING","MPOL_F_RELATIVE_NODES","MPOL_F_STATIC_NODES"]},"mountExtensions":{"idmap":{"enabled":true}},"netDevices":{"enabled":true}},"annotations":{"io.github.seccomp.libseccomp.version":"2.5.4","org.opencontainers.runc.checkpoint.enabled":"true","org.opencontainers.runc.commit":"v1.5.1-0-g8f2685a4","org.opencontainers.runc.version":"1.5.1"},"potentiallyUnsafeConfigAnnotations":["bundle","org.systemd.property.","org.criu.config"]}]}] Default runtime: runc Storage driver: overlayfs Root dir: /var/lib/docker Server version: 29.8.1 ----- running containers ----- NAMES IMAGE STATUS PORTS vllm-embed vllm/vllm-openai:v0.24.0 Up 14 minutes (healthy) 0.0.0.0:8001->8000/tcp, [::]:8001->8000/tcp vllm-rerank-bge vllm/vllm-openai:v0.24.0 Up 15 minutes (healthy) 0.0.0.0:8013->8000/tcp, [::]:8013->8000/tcp ----- all containers ----- NAMES IMAGE STATUS vllm-embed vllm/vllm-openai:v0.24.0 Up 14 minutes (healthy) vllm-rerank-bge vllm/vllm-openai:v0.24.0 Up 15 minutes (healthy) ----- networks ----- NAME DRIVER SCOPE bridge bridge local embed-rerank_default bridge local host host local none null local ----- networks (external, non-default — worth knowing for compose external: true) ----- embed-rerank_default ----- named volumes ----- VOLUME NAME DRIVER ----- compose projects currently running ----- embed-rerank ===== COMPOSE FILES (/opt/docker/compose/) ===== >>> /opt/docker/compose/embed-rerank/compose.yaml # embed-rerank — the fleet's embedding + reranking models, served locally at ESH # on esh-ml1 (CT 110 on esh-pve, RTX 2000E Ada, 16 GB). # # WHY: Prime's decision 2026-09-24 — the Ada card offloads embedding and # reranking so ESH consumers (Open WebUI RAG, Paperless) are not tied to one # seat on fv-ml1. It serves the SAME models as fv-ml1's `vllm` stack, with the # SAME vLLM version and flags, because embedding vectors are model-specific: # a different embedding model here would silently poison every index built # against fv-ml1's. Mirror stacks/vllm/compose.yaml when that changes. # # vllm-embed Qwen/Qwen3-Embedding-0.6B → /v1/embeddings :8001 # vllm-rerank-bge BAAI/bge-reranker-v2-m3 → /rerank, /score :8013 # # Ports match fv-ml1 on purpose, so a LiteLLM deployment for either site # differs only in the host part of api_base. # # `vllm-rerank-bge`, not fv-ml1's `vllm-rerank-a3`: that name carries R43 # bake-off provenance for THAT container; and plain `vllm-rerank` was the # retired Qwen3-Reranker that measured harmful. Name the model instead. # # NO `tnet`/traefik-net: esh-ml1 runs no traefik, and an external network # that does not exist would stop the stack from starting. Consumers reach the # published ports directly. # # Host setup (driver, LXC, docker, toolkit): playbooks/esh-pve-nvidia-host.yaml # then playbooks/esh-ml1-lxc.yaml. Tunables live in .env — edit that, not this. name: embed-rerank services: vllm-embed: image: vllm/vllm-openai:${VLLM_VERSION} container_name: vllm-embed restart: unless-stopped ipc: host ports: - "${EMBED_PORT}:8000" volumes: - /opt/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 - ${EMBED_MAX_MODEL_LEN} - --dtype - auto deploy: resources: reservations: devices: - driver: nvidia device_ids: ["0"] capabilities: [gpu] healthcheck: test: ["CMD", "curl", "-f", "http://localhost:8000/health"] interval: 30s timeout: 10s retries: 3 start_period: 180s labels: - homepage.group=AI - Eval & Retrieval - homepage.name=vLLM Embed (esh-ml1) - homepage.icon=mdi-vector-arrange-below - homepage.description=Qwen3 Embedding 0.6B via vLLM (esh-ml1, RTX 2000E Ada) - homepage.href=http://10.0.50.80:${EMBED_PORT}/docs vllm-rerank-bge: image: vllm/vllm-openai:${VLLM_VERSION} container_name: vllm-rerank-bge restart: unless-stopped ipc: host ports: - "${RERANK_PORT}:8000" volumes: - /opt/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 # bge-reranker-v2-m3 is natively a cross-encoder; no --hf-overrides. - --host - 0.0.0.0 - --port - "8000" - --gpu-memory-utilization - ${RERANK_GPU_MEM_UTIL} - --max-model-len - ${RERANK_MAX_MODEL_LEN} - --dtype - auto deploy: resources: reservations: devices: - driver: nvidia device_ids: ["0"] capabilities: [gpu] healthcheck: test: ["CMD", "curl", "-f", "http://localhost:8000/health"] interval: 30s timeout: 10s retries: 3 start_period: 180s labels: - homepage.group=AI - Eval & Retrieval - homepage.name=vLLM Rerank bge-v2-m3 (esh-ml1) - homepage.icon=mdi-sort-variant - homepage.description=bge-reranker-v2-m3 via vLLM (esh-ml1, RTX 2000E Ada) - homepage.href=http://10.0.50.80:${RERANK_PORT}/docs ===== CONFIG LAYOUT (/opt/docker/conf/ — top 200 entries) ===== /opt/docker/conf ===== LISTENING PORTS ===== *:22 0.0.0.0:8001 0.0.0.0:8013 127.0.0.1:25 [::1]:25 [::]:8001 [::]:8013 ===== MODEL / HUGGINGFACE CACHES ===== ===== DOCKER-ADJACENT SYSTEMD SERVICES ===== container-getty@1.service running container-getty@2.service running containerd.service running docker.service running ===== DONE ===== Paste the above back into the chat, or pass a path as argv[1] to save.