Files
obsidian/phd/weekly-report/260118.md

1.1 KiB

Objectives

  • Auto LLM inference config tuner

Key Results

  • [6/10] Build the agentic tuner system
  • [10/10] Build the first version auto tuner system
  • [2/10] Workload grouping methods
  • [8/10] Check the current situation of parallelism config optimization
  • [4/10] Understand the possibility/challenges in LLM inference compute graph arrangement automatically
  • [1/10] Define the IR for automatic optimization
  • [5/10] Profile different parallelism setup with real trace and analysis their difference

Last Week

  • [KR1] Update agentic AITuner to support new trace benchmark / new vLLM flags/ objective score. 0a012bdd ~ 788da3d8
  • [KR1] Survey the related works. Some works build an agent for LLM training / storage system / ..., a work use BO for LLM inference config tuning.
  • [misc] Prepare an open-sourced version of new traces (thinking and coder) and update readme.

Next Week

  • Optimize the agentic AITuner.
  • Test SCOOT as one of the baseline.