sarman/dgx-spark-playbooks
1
0
Fork 0
mirror of https://github.com/NVIDIA/dgx-spark-playbooks.git synced 2026-04-22 10:03:54 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

chore: Regenerate all playbooks

Browse Source
This commit is contained in:
GitLab CI 2025-10-12 17:11:52 +00:00
parent 56c57950bd
commit 809947301c
1 changed files with 5 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
nvidia/txt2kg/README.md
View File

@ -12,7 +12,7 @@
## Overview
## Basic Idea
## Basic idea
This playbook demonstrates how to build and deploy a comprehensive knowledge graph generation and visualization solution that serves as a reference for knowledge graph extraction.
The unified memory architecture enables running larger, more accurate models that produce higher-quality knowledge graphs and deliver superior downstream GraphRAG performance.
@ -43,16 +43,16 @@ The setup includes:
## Time & risk
**Duration**:
⏱️ **Duration**:
- 2-3 minutes for initial setup and container deployment
- 5-10 minutes for Ollama model download (depending on model size)
- Immediate document processing and knowledge graph generation
**Risks**:
⚠️ **Risks**:
- GPU memory requirements depend on chosen Ollama model size
- Document processing time scales with document size and complexity
**Rollback**: Stop and remove Docker containers, delete downloaded models if needed
↩️ **Rollback**: Stop and remove Docker containers, delete downloaded models if needed
## Instructions
@ -149,7 +149,7 @@ docker exec ollama-compose ollama rm llama3.1:8b
| Symptom | Cause | Fix |
|---------|--------|-----|
| Ollama performance issues | Suboptimal settings for DGX Spark | Set environment variables: `OLLAMA_FLASH_ATTENTION=1` (enables flash attention for better performance), `OLLAMA_KEEP_ALIVE=30m` (keeps model loaded for 30 minutes), `OLLAMA_MAX_LOADED_MODELS=1` (avoids VRAM contention), `OLLAMA_KV_CACHE_TYPE=q8_0` (reduces KV cache VRAM with minimal performance impact) |
| Ollama performance issues | Suboptimal settings for DGX Spark | Set environment variables:<br>`OLLAMA_FLASH_ATTENTION=1` (enables flash attention for better performance)<br>`OLLAMA_KEEP_ALIVE=30m` (keeps model loaded for 30 minutes)<br>`OLLAMA_MAX_LOADED_MODELS=1` (avoids VRAM contention)<br>`OLLAMA_KV_CACHE_TYPE=q8_0` (reduces KV cache VRAM with minimal performance impact) |
| VRAM exhausted or memory pressure (e.g. when switching between Ollama models) | Linux buffer cache consuming GPU memory | Flush buffer cache: `sudo sync; sudo sh -c 'echo 3 > /proc/sys/vm/drop_caches'` |
| Slow triple extraction | Large model or large context window | Reduce document chunk size or use faster models |
| ArangoDB connection refused | Service not fully started | Wait 30s after start.sh, verify with `docker ps` |