Files
obsidian/phd/weekly-report/25/251207.md

1.2 KiB

Objectives

  • Auto LLM inference config tuner

Key Results

  • [7/10] Build the first version auto tuner system
  • [7/10] Check the current situation of parallelism config optimization
  • [4/10] Understand the possibility/challenges in LLM inference compute graph arrangement automatically
  • [0/10] Trace vLLM compute graph and data flow
  • [3/10] Implement a minimal Rust inference framework
  • [1/10] Define the IR for automatic optimization
  • [5/10] Profile different parallelism setup with real trace and analysis their difference
  • [0/10] Meta-analysis for the theory maximum improvement with heterogenous setup [offtrack]

Last Week

  • [KR1] Update workload generator from real workload, give a more precise spec abstraction. c969f366~7407149d
  • [KR1] Benchmark and compare for generated workloads and raw workloads. Find that if input/output length are generated, will cause the performance varies a lot.

Next Week

  • Find the root cause for workload performance variation.
  • Summary the intelligence for auto tuning path.