dgx-spark-playbooks/nvidia/txt2kg/assets/deploy/compose
Santosh Bhavani 529debb633 perf(docker): increase Ollama parallel processing for DGX
- Increase OLLAMA_NUM_PARALLEL from 1 to 4 requests
- Leverage DGX Spark's unified memory architecture
- Improve throughput for concurrent inference requests
2025-10-19 20:56:58 -07:00
..
docker-compose.complete.yml chore: Regenerate all playbooks 2025-10-10 18:45:20 +00:00
docker-compose.optional.yml chore: Regenerate all playbooks 2025-10-10 18:45:20 +00:00
docker-compose.vllm.yml chore: Regenerate all playbooks 2025-10-10 18:45:20 +00:00
docker-compose.yml perf(docker): increase Ollama parallel processing for DGX 2025-10-19 20:56:58 -07:00