Grant
342e150266
Aligned with sibling recipes in eugr/spark-vllm-docker. Applies on next swap to each model. First real swap gemma4 -> qwen36 succeeded in 5:30 with --moe_backend=flashinfer_cutlass.
76 lines
2.9 KiB
Markdown
76 lines
2.9 KiB
Markdown
# spark-control runbook
|
||
|
||
Operating notes for running and maintaining the cluster via spark-control.
|
||
|
||
## Recent successful swaps
|
||
|
||
- **2026-05-12 — gemma4 → qwen36** via `POST /api/swap` from laptop dev server. ~5:30 to "Application startup complete." Inference works (`/v1/chat/completions` returns reasoning content via `reasoning` field). `--moe_backend=flashinfer_cutlass` confirmed valid by vLLM (logged "Using 'FLASHINFER_CUTLASS' NvFp4 MoE backend").
|
||
|
||
## Optimization flags (added 2026-05-12)
|
||
|
||
Aligned `gemma4` and `qwen36` `vllm_args` with the project's sibling recipes (`qwen3.5-35b-a3b-fp8.yaml`, `gemma4-26b-a4b.yaml`):
|
||
|
||
- `--load-format=fastsafetensors` — faster cold-start weight load.
|
||
- `--enable-prefix-caching` — reuse cached prefix tokens (e.g. system prompt) across requests.
|
||
- `--kv-cache-dtype=fp8` — store KV cache in 8-bit FP; halves memory used per active context.
|
||
|
||
These take effect on the **next swap to that model**. If a swap fails after this change with errors mentioning fastsafetensors/prefix-caching/fp8, revert the entry in `models.yaml` and retry.
|
||
|
||
## Day-to-day
|
||
|
||
- The UI lives at `http://<your-start9>.local:9999` once the StartOS package is installed and configured.
|
||
- Status auto-refreshes every 5 s.
|
||
- A swap takes 3–6 minutes depending on the model. Don't close the tab — but if you do, the swap continues; reopen and you'll re-attach to the log stream.
|
||
|
||
## Adding a new model
|
||
|
||
1. Add an entry to `models.yaml` (in the image source) or, post-install, via the "Edit Model Catalog" action in StartOS.
|
||
2. Confirm the weights are on the Spark: `ssh <spark-user>@<spark-1-host>.local 'ls ~/.cache/huggingface/hub/'`. If not, download with `./hf-download.sh <repo>` on Spark 1.
|
||
3. The new model appears in the UI on next refresh.
|
||
|
||
## Manual swap fallback
|
||
|
||
If the UI is unavailable and you need to swap by hand:
|
||
|
||
```bash
|
||
ssh <spark-user>@<spark-1-host>.local
|
||
cd ~/spark-vllm-docker
|
||
./launch-cluster.sh stop
|
||
./launch-cluster.sh --solo -d exec vllm serve RedHatAI/gemma-4-31B-it-NVFP4 \
|
||
--port 8888 --host 0.0.0.0 --gpu-memory-utilization 0.8 \
|
||
--max-model-len 32768 --reasoning-parser gemma4 \
|
||
--tool-call-parser gemma4 --enable-auto-tool-choice
|
||
docker logs -f vllm_node # wait for "Application startup complete."
|
||
```
|
||
|
||
## Diagnostics
|
||
|
||
```bash
|
||
# Is vLLM serving?
|
||
curl -s http://<spark-1-ip>:8888/v1/models | jq .
|
||
|
||
# Cluster status (containers up?)
|
||
ssh <spark-user>@<spark-1-host>.local 'cd ~/spark-vllm-docker && ./launch-cluster.sh status'
|
||
|
||
# Tail current model's logs
|
||
ssh <spark-user>@<spark-1-host>.local 'docker logs --tail 200 -f vllm_node'
|
||
|
||
# Parakeet
|
||
curl -s http://<spark-2-ip>:8000/health
|
||
|
||
# Magpie (see known-issues.md)
|
||
curl -s http://<spark-2-ip>:9000/v1/health/ready
|
||
```
|
||
|
||
## Hard reset
|
||
|
||
If launch-cluster.sh gets stuck:
|
||
|
||
```bash
|
||
ssh <spark-user>@<spark-1-host>.local
|
||
cd ~/spark-vllm-docker
|
||
./launch-cluster.sh stop
|
||
docker ps -aq | xargs -r docker rm -f
|
||
# then relaunch your preferred model
|
||
```
|