# esh-ml1

GPU LXC for the ESH home lab: **CT 110 on esh-pve**, holding the **NVIDIA RTX
2000E Ada** (16 GB, 50 W, `01:00.0`). It serves the fleet's embedding and
reranking models locally at ESH. Built 2026-09-24.

| | |
|---|---|
| **IP** | `10.0.50.80/24`, VLAN 50, gateway `10.0.50.1` (static, outside the UDM's `.150–.250` DHCP pool) |
| **DNS** | `esh-ml1.esh.internal` |
| **SSH** | `ssh esh-ml1` → `infra-ops@10.0.50.80` (NOPASSWD sudo) · from the host: `pct enter 110` |
| **OS** | Debian 12, unprivileged, `nesting=1,keyctl=1` |
| **Size** | 6 cores, 16 GB RAM + 2 GB swap, 80 GB rootfs on `local-lvm` |
| **Boot** | `onboot: 1`, `startup: order=30` — after esh-scale (1), esh-vm-db (10) and esh-vm-docker (20), so a GPU fault never delays ESH's DNS or mesh route |
| **Backups** | **None, on purpose.** esh-pve's vzdump job lists vmids explicitly and 110 is not one. Everything is rebuilt from the playbooks and the stack; models re-download. |

## What it serves

`stacks/embed-rerank` (`/opt/docker/compose/embed-rerank`):

| container | model | port | gateway name |
|---|---|---|---|
| `vllm-embed` | `Qwen/Qwen3-Embedding-0.6B` | 8001 | `qwen3-embedding` (order 2) |
| `vllm-rerank-bge` | `BAAI/bge-reranker-v2-m3` | 8013 | `reranker` (order 2) |

The same models, vLLM version (`v0.24.0`, digest `251eba5cc7c1`) and flags as
fv-ml1's `vllm` stack, so the two sites are interchangeable. In LiteLLM they
are the **order-2 failover** behind fv-ml1: fv-ml1 serves every request while
it is up.

**Parity, measured 2026-09-24** (11 texts incl. CJK, code, a 6k-char passage;
2 runs per site):

| | median | min |
|---|---|---|
| embed cosine FV vs ESH, same text | 0.999908 | 0.999772 |
| noise floor FV vs FV | 0.999927 | 0.999791 |
| noise floor ESH vs ESH | 0.999911 | 0.999809 |
| negative control, different texts | 0.232 | 0.071 |

The cross-site difference is inside each site's own run-to-run noise; this
method cannot resolve a cosine gap below ~2×10⁻⁴. Reranker scores differed by
at most 0.000145 (FV-vs-FV floor 0.000181), with identical ranking.

**Speed vs fv-ml1, measured 2026-09-25 0628–0640 PT** (same vLLM v0.24.0 and
flags; fv-ml1 GPU 1 is shared with other seats but read 0% util before and
after; synthetic text; each cell = median of 6 reps = 2 interleaved runs × 3):

| workload | on-box FV | on-box ESH | from ana-docker FV | from ana-docker ESH |
|---|---|---|---|---|
| embed 1 query, p50 | ~12 ms | ~9 ms | ~29 ms | ~23 ms |
| embed 1 × ~512 tok, p50 | ~15 ms | ~23 ms | ~31 ms | ~31 ms |
| embed 1 × ~2k tok, p50 | ~25 ms | ~86 ms | ~48 ms | ~90 ms |
| bulk embed, passages/s (64×512 tok, conc 4) | ~403 | ~50 | ~374 | ~51 |
| rerank 20 docs, p50 | ~51 ms | ~170 ms | ~82 ms | ~175 ms |
| rerank 20 docs, req/s at conc 8 | ~55 | ~5.7 | ~52 | ~5.9 |

Read it as: **single queries are a wash** (ESH is ~6 ms faster from the gateway
because it is closer — 6 ms RTT vs 17.6 ms), **anything bulk is 3–10× slower**
on the 50 W Ada. Noise floor (run vs run, same site): ~3–5% on throughput, ±3 ms
on small-query latency on fv-ml1, so the small-query rows cannot rank the sites.
Positive control: 2k-token inputs were slower than 512-token ones on both
sites. One fv-ml1 rep of the gateway-vantage rerank burst stalled to 1.0 req/s
(64 requests in ~64 s); it did not recur in 11 other reps — unexplained, n=1.
**Consequence: keep esh-ml1 as failover, don't load-share** — sharing would
roughly double rerank latency for half the fleet's calls.

**Whole-novel embedding, measured 2026-09-25 0653–0717 PT** — *The Stand*
(uncut, ~1,150 pages): 470,783 words, 12,814 `<p>` paragraphs (median 22 words),
617,833 tokens. Client on nh3-dev (where worldtree-gateway runs); 3 reps each:

| how | fv-ml1 | esh-ml1 |
|---|---|---|
| via gateway, 1 paragraph per request (1,000-para sample, scaled) | 59.8 ms/para → ~12.8 min | 55.3 ms/para → ~11.8 min |
| via gateway, 64 per request, 1 at a time | 100–123 s | 91–100 s |
| via gateway, 64 per request, 4 in flight | 46–54 s | 45–50 s |
| direct to the seat, 64 per request, 4 in flight | 13.4–14.1 s | 28.8–29.6 s |

Through the gateway the GPU is not the bottleneck: one-per-request is network +
LiteLLM overhead, and batched runs pinned LiteLLM at ~76% CPU (64×1024-float
JSON per response). Only the direct path shows the card: esh-ml1 is ~2.2×
slower, ~21k vs ~45k tokens/s.

**VRAM:** 0.20 × 16,380 MiB each; 4,823 MiB in use with both loaded, ~11 GB
free.

## How it is built

1. [`playbooks/esh-pve-nvidia-host.yaml`](../../playbooks/esh-pve-nvidia-host.yaml)
   — driver **580.178.04** (open modules, DKMS) on the **hypervisor**, the
   `nvidia-persistenced` unit that creates the device nodes before
   `pve-guests`, and removal of the old VFIO/blacklist config.
2. [`playbooks/esh-ml1-lxc.yaml`](../../playbooks/esh-ml1-lxc.yaml) — the CT,
   `dev0–3` GPU nodes, the NVIDIA userspace from the **same `.run`** with
   `--no-kernel-modules`, fleet ids (infra-ops 850, docker 851, vh 1000),
   docker-ce and nvidia-container-toolkit with `no-cgroups = true`.
3. `scripts/deploy-stack.sh esh-ml1 embed-rerank`, then `docker compose up -d`.

Both playbooks are idempotent; re-run them to repair.

## ⚠ Driver version lock

The kernel module lives on esh-pve; the libraries live in this container. They
**must be the same version**, or every CUDA call fails with *"driver/library
version mismatch"*. To upgrade: bump `driver_version` + `driver_sha256` in the
host playbook and `driver_version` in the LXC playbook, run the host one, then
the LXC one, then restart the stack.

A PVE kernel update is handled by DKMS (`proxmox-headers-6.8` pulls headers
for each new kernel). Moving esh-pve to a different kernel series (6.14 opt-in)
needs that series' headers meta-package installed first, or the module will not
build and this CT will fail to start at the next boot.

## Not yet wired

- **Homepage**: the compose carries labels, but esh-ml1 is not in
  `stacks/homepage/conf/docker.yaml` (it would need dockerd on tcp/2375 like
  the other hosts).
- **Beszel**: no agent yet.
- **ESH consumers** (Open WebUI RAG, Paperless) still go through the gateway
  at ana-docker, so they do not survive a mesh outage. See persistent-memory
  for the open decision.