gemma3-vllm-stack/docs/TROUBLESHOOTING.md

Troubleshooting

ROCm devices not visible in host

Symptoms:

• /dev/kfd missing
• /dev/dri missing
• vLLM fails to start with ROCm device errors

Checks:

ls -l /dev/kfd /dev/dri
id
getent group video

Expected:

• /dev/kfd exists
• /dev/dri directory exists
• user belongs to video group

Fixes:

sudo usermod -aG video "$USER"
newgrp video

Then verify ROCm tools:

rocminfo | sed -n '1,120p'

If ROCm is not healthy, fix host ROCm installation first.

---

Docker and Compose not available

Symptoms:

• docker: command not found
• docker compose version fails

Checks:

docker --version
docker compose version

Fix using install script (Ubuntu):

./scripts/install.sh

Manual fallback:

sudo apt-get update
sudo apt-get install -y ca-certificates curl gnupg
sudo install -m 0755 -d /etc/apt/keyrings
curl -fsSL https://download.docker.com/linux/ubuntu/gpg | sudo gpg --dearmor -o /etc/apt/keyrings/docker.gpg
sudo chmod a+r /etc/apt/keyrings/docker.gpg
echo "deb [arch=$(dpkg --print-architecture) signed-by=/etc/apt/keyrings/docker.gpg] https://download.docker.com/linux/ubuntu jammy stable" | sudo tee /etc/apt/sources.list.d/docker.list >/dev/null
sudo apt-get update
sudo apt-get install -y docker-ce docker-ce-cli containerd.io docker-buildx-plugin docker-compose-plugin
sudo usermod -aG docker "$USER"

Log out/in after group change.

---

vLLM container exits or fails healthchecks

Symptoms:

• gemma3-vllm restarting
• API endpoint unavailable

Checks:

docker compose ps
docker compose logs --tail=200 gemma3-vllm

Common causes and fixes:

1. Missing/invalid Hugging Face token:

grep -E '^(HF_TOKEN|GEMMA_MODEL_ID)=' .env

Ensure HF_TOKEN is set to a valid token with access to Gemma 3.

2. Model ID typo:

grep '^GEMMA_MODEL_ID=' .env

Use a valid model, e.g. google/gemma-3-1b-it.

3. ROCm runtime/device issues:

docker run --rm --device=/dev/kfd --device=/dev/dri --group-add video ubuntu:22.04 bash -lc 'ls -l /dev/kfd /dev/dri'

4. API key mismatch between backend and UI/tests:

grep -E '^(VLLM_API_KEY|OPENAI_API_BASE_URL)=' .env frontend/config/frontend.env 2>/dev/null || true

Keep keys consistent.

---

Out-of-memory (OOM) or low VRAM errors

Symptoms:

• startup failure referencing memory allocation
• runtime generation failures

Checks:

docker compose logs --tail=300 gemma3-vllm | grep -Ei 'out of memory|oom|memory|cuda|hip|rocm'

Mitigations:

1. Reduce context length in .env:

VLLM_MAX_MODEL_LEN=2048

2. Lower GPU memory utilization target:

VLLM_GPU_MEMORY_UTILIZATION=0.75

3. Use a smaller Gemma 3 variant in .env.
4. Restart stack:

./scripts/restart.sh

---

UI loads but cannot reach vLLM backend

Symptoms:

• Browser opens UI but chat requests fail.

Checks:

docker compose ps
docker compose logs --tail=200 chat-ui
docker compose logs --tail=200 gemma3-vllm

Verify frontend backend URL:

grep -E '^OPENAI_API_BASE_URL=' frontend/config/frontend.env

Expected value:

OPENAI_API_BASE_URL=http://gemma3-vllm:8000/v1

Verify API directly from host:

./scripts/test_api.sh

If API works from host but not UI, recreate frontend:

docker compose up -d --force-recreate chat-ui

---

Health checks and endpoint validation

Run all smoke tests:

./scripts/test_api.sh
./scripts/test_ui.sh
python3 scripts/test_python_client.py

If one fails, inspect corresponding service logs and then restart:

docker compose logs --tail=200 gemma3-vllm chat-ui
./scripts/restart.sh