[None][test] Update case that not support passing quantization fp8 for pytorch backend (#7302)

Signed-off-by: nvamyt <[email protected]>

Author: nvamyt

tests/integration/test_lists/qa/llm_perf_sanity.yml

@@ -191,8 +191,8 @@ llm_perf_sanity:
 
   tests:
   #llama_v3.1_70b
-  #pytorch backend
-  - perf/test_perf.py::test_perf[llama_v3.1_70b-bench-pytorch-bfloat16-maxbs:1-input_output_len:512,32-quant:fp8-gpus:8]
+  #trt backend
+  - perf/test_perf.py::test_perf[llama_v3.1_70b-bench-bfloat16-maxbs:1-maxnt:544-input_output_len:512,32-quant:fp8-gpus:8]
   #llama_v3.3_70b_instruct_fp8
   #pytorch backend
   - perf/test_perf.py::test_perf[llama_v3.3_70b_instruct_fp8-bench-pytorch-float8-input_output_len:128,128-gpus:8]