Files

T

vh 40a374b809 feat(vllm): add phi4-mini FP8 summarizer/dreamer on ana-ml2; retire granite from llama-swap

phi4-mini supersedes the granite-4-small llama-swap pin as the summarizer +
dreaming agent. New vllm-phi4 service: Phi-4-mini-instruct, vLLM-native FP8
(near-lossless on RTX 6000 Ada cc 8.9), 50K ctx, FP8 KV cache, GPU 1, :8004.

llama-swap: removed granite-4-small (depinned) + granite-4-micro config —
both superseded. CONFIG ONLY; the GGUFs stay on disk. Frees granite-4-small's
~24 GB (it was pinned at 120K ctx).

Placement: phi4 on GPU 1 with the embed/rerank/reward trio (~1.2 GB margin at
50K); keeps GPU 0 clear for llama-swap heavy models. docs/roadmap.md captures
the deferred vLLM observability (Langfuse req/resp tracing + Prometheus/Grafana).

Deploy order: llama-swap config (free granite) -> vllm-phi4 -> repoint nevermore.

2026-06-03 23:21:45 -07:00

conf

feat(vllm): add phi4-mini FP8 summarizer/dreamer on ana-ml2; retire granite from llama-swap

2026-06-03 23:21:45 -07:00

.env.example

Initial commit: PFI fleet inventory, stacks, tooling, and backup pipeline

2026-04-20 14:29:48 -07:00

compose.yaml

Initial commit: PFI fleet inventory, stacks, tooling, and backup pipeline

2026-04-20 14:29:48 -07:00

README.md

vllm: rename stack from vllm-qwen3 → vllm + add Skywork reward classifier

2026-05-13 22:00:26 -07:00

README.md

llama-swap

GGUF model server with on-demand model swapping. Served via llama.cpp's llama-server under the llama-swap proxy.

Server: ana-ml2 Port: 9292 (configurable via .env) GPU: both (unpinned — runtime: nvidia grants access to all devices; per-model GPU selection happens inside config.yaml)

Files

compose.yaml — canonical compose. Deployed to /opt/docker/compose/llama-swap/compose.yaml on ana-ml2.
.env.example — template for the per-host .env. Copy to .env on the server and tweak.
config.yaml — model definitions and groups. Deployed to /opt/docker/conf/llama-swap/config.yaml on the server.

Homepage labels are in the compose file under the AI Systems group, matching the convention used by vllm and infinity.

Deploy a fresh install

scripts/deploy-stack.sh ana-ml2 llama-swap

ssh ana-ml2 '
  cd /opt/docker/compose/llama-swap && \
  cp -n .env.example .env && \
  docker compose config && \
  docker compose up -d && \
  docker compose logs --tail=30
'

Model reference conventions

Modern entries: use -hf <user>/<repo>[:<quant>] — reads from the shared HF cache, nothing to pre-stage outside hf download
Legacy entries: use --model /models/<dir>/<file>.gguf — reads GGUFs from /tank/aimodels/llm/ (pre-HF-cache era, gradually being migrated)

New models should prefer the -hf pattern.

Deploy updates to config only

# After editing config.yaml here:
scp config.yaml ana-ml2:/opt/docker/conf/llama-swap/config.yaml
ssh ana-ml2 'cd /opt/docker/compose/llama-swap && docker compose restart'

Deploy updates to compose only

# After editing compose.yaml or .env.example here:
scripts/deploy-stack.sh ana-ml2 llama-swap
ssh ana-ml2 'cd /opt/docker/compose/llama-swap && docker compose up -d'