default config

Author: chibu

examples/guidellm_example.py

@@ -11,10 +11,9 @@
     GUIDELLM__MAX_CONCURRENCY=256,
     GUIDELLM__REQUEST_TIMEOUT=21600,
     target="http://localhost:8000/v1",
-    #data_type="emulated",
     max_seconds=30,
-    #config = "benchmarking_32k",
-    #data="prompt_tokens=128,output_tokens=128",
+    scenario = "benchmarking_32kz",
+    data="prompt_tokens=128,output_tokens=128",
     branch = "update_guidellm",
     vllm_kwargs={"enable-chunked-prefill": True}
 )

src/automation/configs.py

@@ -1,7 +1,5 @@
-#DEFAULT_DOCKER_IMAGE = "498127099666.dkr.ecr.us-east-1.amazonaws.com/mlops/k8s-research-cuda12_5:latest"
 DEFAULT_DOCKER_IMAGE = "498127099666.dkr.ecr.us-east-1.amazonaws.com/mlops/k8s-research-cuda12_8:latest"
 #DEFAULT_OUTPUT_URI = "gs://neuralmagic-clearml"
 DEFAULT_OUTPUT_URI = "http://10.128.20.60:8081"
 DEFAULT_RESEARCH_BRANCH = "main"
 DEFAULT_GUIDELLM_SCENARIO = "chat"
-#DEFAULT_GUIDELLM_SCENARIO = "benchmarking_summarization"