DeepSeek V3.2 (685B) Validation Testing

Concurrency Scaling

Scaling Results

Observations:

• Strong scaling from 5 to 50 concurrent requests
• Peak scaling throughput of 2,011 tok/s at 50 concurrent
• Saturation detected at 75 concurrent (throughput plateau)
• MLA architecture shows efficient batching up to saturation point

Stress Tests

Key findings:

• Long output generation (500 tokens): 288 tok/s with 20.5s p99 latency
• Long context (4K tokens): 1,801 tok/s with 9.6s p99 latency

Saturation Testing

Extreme Load Results

Observations:

• Peak throughput of 5,519 tok/s achieved at 200 concurrent
• Saturation begins at 200 concurrent requests
• 100% success rate maintained even under extreme load
• Consistent ~5,200-5,500 tok/s across 150-500 concurrent

Recommendations

Test Configuration

Launch Command

docker run --rm \
  --group-add=video \
  --cap-add=SYS_PTRACE \
  --security-opt seccomp=unconfined \
  --device /dev/kfd \
  --device /dev/dri \
  -v ~/.cache/huggingface:/root/.cache/huggingface \
  --env "HF_TOKEN=$HF_TOKEN" \
  --env "VLLM_ROCM_USE_AITER=1" \
  --env "AITER_ENABLE_VSKIP=0" \
  -p 8000:8000 \
  --ipc=host \
  vllm/vllm-openai-rocm:latest \
  --model deepseek-ai/DeepSeek-V3.2 \
  --tensor-parallel-size 8 \
  --block-size 1 \
  --quantization fp8

Test Environment