vh
2c3ef7a8af
Prime's call via brokkr: h2o-lightning-4b replaces the intern-decision seat once
albok-dev re-validates Nemi's sensitivity judge on it. services/h2o-decision-front
builds on infra-hermes's admission proxy (30f36f2): 32,000-token refuse-not-trim,
the seat's bearer token, and intern-decision-serve's /decide/shared mapping onto
/v1/systemone so the judge runs unchanged. stacks/h2o-eval serves it on GPU 3
:8034 exactly as benched (vLLM 0.30.0 + unmodified vendor shim; weights hashed
against HF b43f759b). INC keeps serving production on GPU 1.
57 lines
2.4 KiB
YAML
57 lines
2.4 KiB
YAML
# TEMPORARY h2o-lightning-4b decision seat on fv-ml1 GPU 3 (Prime 2026-10-12 via brokkr: "stand up the h2o copy on
|
|
# gpu 3 if you need to test, it should replace the live seat as soon as possible and keep gpu3 only for transient
|
|
# tasks"). It exists so albok-dev can re-validate Nemi's sensitivity judge on h2o before the GPU 1 cutover; REMOVE it
|
|
# right after the cutover. INC (stacks/intern-decision) keeps serving production on GPU 1 meanwhile.
|
|
# Serving exactly as benched (docs/pfi/decision-sweep-followon-bench-2026-10-12.md, Amendment 1): stock vLLM 0.30.0
|
|
# + the vendor's unmodified shim + the admission front (services/h2o-decision-front, copied into conf/front).
|
|
# Weights: /tank/aimodels/h2o-lightning-4b-b43f759b (hashes match HF at b43f759b; see the stack README).
|
|
name: h2o-eval
|
|
services:
|
|
vllm:
|
|
image: vllm/vllm-openai:v0.30.0
|
|
container_name: h2o-eval-vllm
|
|
restart: unless-stopped
|
|
ports:
|
|
- "127.0.0.1:18199:8000"
|
|
environment:
|
|
VLLM_USE_FLASHINFER_SAMPLER: "0"
|
|
volumes:
|
|
- /tank/aimodels/h2o-lightning-4b-b43f759b:/model:ro
|
|
- h2o-eval-vllm-cache:/root/.cache/vllm
|
|
command: ["--model", "/model", "--served-model-name", "h2oai/h2o-lightning-4b",
|
|
"--max-model-len", "40960", "--max-num-seqs", "16", "--gpu-memory-utilization", "0.1506",
|
|
"--limit-mm-per-prompt", "{\"image\": 4, \"video\": 0}",
|
|
"--mm-processor-kwargs", "{\"max_pixels\": 1605632}"]
|
|
deploy:
|
|
resources:
|
|
reservations:
|
|
devices:
|
|
- driver: nvidia
|
|
device_ids: ["3"]
|
|
capabilities: [gpu]
|
|
front:
|
|
image: python:3.12-slim
|
|
container_name: h2o-eval-front
|
|
restart: unless-stopped
|
|
network_mode: host
|
|
depends_on: [vllm]
|
|
env_file: .env
|
|
environment:
|
|
SHIM_VLLM: http://127.0.0.1:18199
|
|
SHIM_PORT: "18191"
|
|
SHIM_NOUL_FLOOR: "0.801"
|
|
FRONT_SHIM: http://127.0.0.1:18191
|
|
FRONT_VLLM: http://127.0.0.1:18199
|
|
FRONT_BIND: 0.0.0.0
|
|
FRONT_PORT: "8034"
|
|
FRONT_CAP: "32000"
|
|
FRONT_SHIM_FILE: /model/h2o_lightning_shim.py
|
|
FRONT_SERVE_CONFIG: /model/serve_config.json
|
|
FRONT_MODEL_REVISION: b43f759b6385d21182f87c3829931ec3d4dfa98a
|
|
volumes:
|
|
- /tank/aimodels/h2o-lightning-4b-b43f759b:/model:ro
|
|
- /opt/docker/conf/h2o-eval/front:/front:ro
|
|
command: ["bash", "/front/run.sh"]
|
|
volumes:
|
|
h2o-eval-vllm-cache:
|