feat: Add TTFT and ITL Interpolation to Profiling Script (#1159)

Co-authored-by: root <root@kkranen-dt.nvidia.com>

container/deps/requirements.txt

@@ -31,6 +31,7 @@ protobuf==5.27.3
 pydantic==2.7.1
 pyright
 PyYAML
+scikit-learn
 sentencepiece
 tensorboard==2.19.0
 tensorboardX==2.6.2.2

docs/guides/planner.md

@@ -86,6 +86,8 @@ The following information will be printed out in the terminal:
 2025-05-16 15:20:24 - __main__ - INFO - Suggested planner upper/lower bound for decode kv cache utilization: 0.20/0.10
 ```
 
+After finding the best TP size for prefill and decode, the script will then interpolate the TTFT with ISL and ITL with active KV cache and decode context length. This is to provide a more accurate estimation of the performance when ISL and OSL changes. The results will be saved to `<output_dir>/<decode/prefill>_tp<best_tp>_interploation`.
+
 ## Usage
 The planner is started automatically as part of Dynamo pipelines when running `dynamo serve`. You can configure the planner just as you would any other component in your pipeline either via YAML configuration or through CLI arguments.