Merge 050f799875 into 08c06d5bd9

nvidia/nemo-fine-tune/README.md

@@ -47,8 +47,8 @@ All necessary files for the playbook can be found [here on GitHub](https://githu
 * **Duration:** 45-90 minutes for complete setup and initial model fine-tuning
 * **Risks:** Model downloads can be large (several GB), ARM64 package compatibility issues may require troubleshooting, distributed training setup complexity increases with multi-node configurations
 * **Rollback:** Virtual environments can be completely removed; no system-level changes are made to the host system beyond package installations.
-* **Last Updated:** 03/04/2026
+* **Last Updated:** 01/15/2026
-  * Recommend running Nemo finetune workflow via Docker
+  * Fix qLoRA fine-tuning workflow
 
 ## Instructions
 

nvidia/txt2kg/assets/deploy/compose/docker-compose.yml

@@ -27,8 +27,8 @@ services:
       # Ollama configuration
       - OLLAMA_BASE_URL=http://ollama:11434/v1
       - OLLAMA_MODEL=llama3.1:8b
-      # vLLM disabled in default Ollama mode
+      # Disable vLLM
-      # - VLLM_BASE_URL=http://localhost:8001/v1
+      - VLLM_BASE_URL=http://localhost:8001/v1
       - VLLM_MODEL=disabled
       # Vector DB configuration
       - QDRANT_URL=http://qdrant:6333

nvidia/txt2kg/assets/frontend/lib/text-processor.ts

@@ -108,7 +108,7 @@ export class TextProcessor {
     
     // Determine which LLM provider to use based on configuration
     // Priority: vLLM > NVIDIA > Ollama
-    if (process.env.VLLM_BASE_URL && process.env.VLLM_MODEL && process.env.VLLM_MODEL !== 'disabled') {
+    if (process.env.VLLM_BASE_URL) {
       this.selectedLLMProvider = 'vllm';
     } else if (process.env.NVIDIA_API_KEY) {
       this.selectedLLMProvider = 'nvidia';