edits

Author: sidsingh-nvidia

tests/functional_tests/test_cases/gpt/gpt_dynamic_inference_tp1_pp1_583m_cuda_graphs_logitsmatch_decode_graphs_only/model_config.yaml.tmp

@@ -51,7 +51,7 @@ MODEL_ARGS:
   --prompts: "Time travel to 2008, and go to a bar or a club or one of the myriad disco-basements on the Lower East Side that does not quite know which of those it is. Dance awkwardly in a room full of other glittered-up nerds, and wait for something to happen, buoyed on the feeling that this is the big swollen heart of life, that this is New York like the movies."
   --incoming-requests-per-step: 32
   --use-flashinfer-fused-rope: true
-  --use-inference-optimized-layers: tru
+  --use-inference-optimized-layers: true
 
 METRICS:
   - "generated_tokens"