Add GPU Lab configs, docs, and runbooks for VM303.

Mirror gpu-lab compose files and model-manager catalog from GPU-Dev; document Dockhand mapping and SGLang cutover target.

config/gpu-lab/RUNBOOK.md

@@ -0,0 +1,61 @@
+# GPU Lab Runbook — VM303 (atc-gpu-dev)
+
+## Runtimes (Docker)
+
+| Runtime ID | Compose | Image |
+|---|---|---|
+| `vllm-legacy-040` | `compose.vllm-legacy.yml` | `vllm/vllm-openai:v0.4.0.post1` |
+| `vllm-modern-080` | `compose.vllm-modern.yml` | `vllm/vllm-openai:v0.8.5.post1` |
+| `sglang-modern` | `compose.sglang.yml` | `lmsysorg/sglang:v0.5.12-cu129-runtime` |
+
+Only **one** inference container runs at a time (port **8010**).
+
+## Activate (UI)
+
+GPU Lab → pick model → **Activate**. Writes `/root/gpu-lab/active/current.env`, stops all gpu-lab containers, starts the matching compose stack.
+
+## Manual activate
+
+```bash
+cd /root/gpu-lab
+# edit active/current.env (MODEL_PATH, TP_SIZE, VLLM_EXTRA_ARGS, …)
+docker compose -f compose.vllm-legacy.yml down
+docker compose -f compose.vllm-legacy.yml up -d
+curl -s http://127.0.0.1:8010/v1/models
+```
+
+## Rollback to systemd vLLM
+
+```bash
+cd /root/gpu-lab
+docker compose -f compose.vllm-legacy.yml down
+docker compose -f compose.vllm-modern.yml down
+docker compose -f compose.sglang.yml down
+systemctl start vllm.service
+systemctl restart vllm-gateway.service litellm-proxy.service
+```
+
+## Logs
+
+```bash
+docker logs -f gpu-lab-vllm-legacy
+docker logs -f gpu-lab-vllm-modern
+docker logs -f gpu-lab-sglang
+journalctl -u model-manager -f
+```
+
+## SGLang on V100
+
+Always use `--disable-flashinfer` and `--disable-flashinfer-sampling` (already in compose.sglang.yml).
+
+## Dockhand
+
+- Environment **GPU-Dev** → `10.0.20.106:2375`
+- Stacks: `gpu-lab-vllm-legacy`, `gpu-lab-vllm-modern`, `gpu-lab-sglang` (compose in Dockhand data volume)
+- Running workload appears as stack **`gpu-lab`** (compose project on VM303)
+- API: `GET /api/stacks?env=8` (not `environmentId`)
+- UI: http://atc-docker01.dell-atc.lan:8082/
+
+## Docker data
+
+Images stored under `/root/docker-data` (not `/var` — small partition).

config/gpu-lab/compose.sglang.yml

@@ -0,0 +1,38 @@
+name: gpu-lab-sglang
+services:
+  sglang:
+    image: lmsysorg/sglang:v0.5.12-cu129-runtime
+    container_name: gpu-lab-sglang
+    network_mode: host
+    ipc: host
+    shm_size: "32gb"
+    env_file:
+      - active/current.env
+    volumes:
+      - /root/models:/models:ro
+    deploy:
+      resources:
+        reservations:
+          devices:
+            - driver: nvidia
+              count: all
+              capabilities: [gpu]
+    entrypoint: ["python3", "-m", "sglang.launch_server"]
+    command:
+      - --model-path
+      - ${MODEL_PATH}
+      - --served-model-name
+      - ${SERVED_NAME}
+      - --host
+      - "0.0.0.0"
+      - --port
+      - "8010"
+      - --tp-size
+      - ${TP_SIZE}
+      - --mem-fraction-static
+      - ${GPU_MEM_UTIL}
+      - --context-length
+      - ${MAX_MODEL_LEN}
+      - --disable-flashinfer
+      - --disable-flashinfer-sampling
+    restart: "no"

config/gpu-lab/compose.vllm-legacy.yml

@@ -0,0 +1,33 @@
+name: gpu-lab-vllm-legacy
+services:
+  vllm-legacy:
+    image: vllm/vllm-openai:v0.4.0.post1
+    container_name: gpu-lab-vllm-legacy
+    network_mode: host
+    ipc: host
+    shm_size: "32gb"
+    env_file:
+      - active/current.env
+    volumes:
+      - /root/models:/models:ro
+    deploy:
+      resources:
+        reservations:
+          devices:
+            - driver: nvidia
+              count: all
+              capabilities: [gpu]
+    entrypoint: ["/bin/sh", "-c"]
+    command:
+      - >
+        exec python3 -m vllm.entrypoints.openai.api_server
+        --model "$$MODEL_PATH"
+        --served-model-name "$$SERVED_NAME"
+        --host 0.0.0.0 --port 8010
+        --tensor-parallel-size "$$TP_SIZE"
+        --dtype "$$DTYPE"
+        --max-model-len "$$MAX_MODEL_LEN"
+        --gpu-memory-utilization "$$GPU_MEM_UTIL"
+        --max-num-seqs "$$MAX_NUM_SEQS"
+        $$VLLM_EXTRA_ARGS
+    restart: "no"

config/gpu-lab/compose.vllm-modern.yml

@@ -0,0 +1,34 @@
+name: gpu-lab-vllm-modern
+services:
+  vllm-modern:
+    image: vllm/vllm-openai:v0.8.5.post1
+    container_name: gpu-lab-vllm-modern
+    network_mode: host
+    ipc: host
+    shm_size: "32gb"
+    env_file:
+      - active/current.env
+    volumes:
+      - /root/models:/models:ro
+    deploy:
+      resources:
+        reservations:
+          devices:
+            - driver: nvidia
+              count: all
+              capabilities: [gpu]
+    entrypoint: ["/bin/sh", "-c"]
+    command:
+      - >
+        exec python3 -m vllm.entrypoints.openai.api_server
+        --model "$$MODEL_PATH"
+        --served-model-name "$$SERVED_NAME"
+        --host 0.0.0.0 --port 8010
+        --tensor-parallel-size "$$TP_SIZE"
+        --dtype "$$DTYPE"
+        --max-model-len "$$MAX_MODEL_LEN"
+        --gpu-memory-utilization "$$GPU_MEM_UTIL"
+        --max-num-seqs "$$MAX_NUM_SEQS"
+        --trust-remote-code --enforce-eager
+        $$VLLM_EXTRA_ARGS
+    restart: "no"

config/gpu-lab/runtimes.json

@@ -0,0 +1,24 @@
+{
+  "vllm-legacy-040": {
+    "engine": "vllm",
+    "compose_file": "compose.vllm-legacy.yml",
+    "image": "vllm/vllm-openai:v0.4.0.post1",
+    "v100_ok": true,
+    "label": "vLLM 0.4"
+  },
+  "vllm-modern-080": {
+    "engine": "vllm",
+    "compose_file": "compose.vllm-modern.yml",
+    "image": "vllm/vllm-openai:v0.8.5.post1",
+    "v100_ok": true,
+    "label": "vLLM 0.8"
+  },
+  "sglang-modern": {
+    "engine": "sglang",
+    "compose_file": "compose.sglang.yml",
+    "image": "lmsysorg/sglang:v0.5.12-cu129-runtime",
+    "v100_ok": true,
+    "label": "SGLang",
+    "extra_args": ["--disable-flashinfer", "--disable-flashinfer-sampling"]
+  }
+}