Merge branch 'main' into multiple-model-with-remote-service

sgurunat · Nov 12, 2024 · 96e797e · 96e797e
2 parents c88d9d7 + f7a7f8a
commit 96e797e
Show file tree

Hide file tree

Showing 2 changed files with 3 additions and 3 deletions.
diff --git a/ChatQnA/benchmark/performance/kubernetes/intel/gaudi/README.md b/ChatQnA/benchmark/performance/kubernetes/intel/gaudi/README.md
@@ -100,12 +100,12 @@ python deploy.py --uninstall
 #### Case 2: Baseline Deployment without Rerank
 
 ```bash
-python deploy.py --hftoken $HFTOKEN --modeldir $MODELDIR --num-nodes 2
+python deploy.py --hf-token $HFTOKEN --model-dir $MODELDIR --num-nodes 2
 ```
 #### Case 3: Tuned Deployment with Rerank
 
 ```bash
-python deploy.py --hftoken $HFTOKEN --modeldir $MODELDIR --num-nodes 2 --with-rerank --tuned
+python deploy.py --hf-token $HFTOKEN --model-dir $MODELDIR --num-nodes 2 --with-rerank --tuned
 ```
 
 ## Benchmark

diff --git a/ChatQnA/benchmark/performance/kubernetes/intel/gaudi/generate_helm_values.py b/ChatQnA/benchmark/performance/kubernetes/intel/gaudi/generate_helm_values.py
@@ -99,7 +99,7 @@ def generate_helm_values(with_rerank, num_nodes, hf_token, model_dir, node_selec
             },
             {"name": "teirerank", "resources": {"limits": {"habana.ai/gaudi": 1}}} if with_rerank else None,
             {"name": "tgi", "resources": {"limits": {"habana.ai/gaudi": 1}}},
-            {"name": "retriever", "resources": {"requests": {"cpu": "8", "memory": "8000Mi"}}},
+            {"name": "retriever-usvc", "resources": {"requests": {"cpu": "8", "memory": "8000Mi"}}},
         ]
 
         # Filter out any None values directly as part of initialization