Repositories list

• MLKV

  Public
  MLKV: Efficiently Scaling up Large Embedding Model Training with Disk-based Key-Value Storage (ICDE 2025 Industry Track)

  machine-learningrecommender-systemknowledge-graph-embeddings+ 2graph-neural-networkskey-value-storage

  MIT License

  •0•6•0•0•Updated May 31, 2025May 31, 2025

• llmstation

  Public
  Resource Multiplexing in Tuning and Serving Large Language Models (USENIX ATC 2025)

  inferencepytorchlora+ 4fine-tuningpeftllmco-serving

  Python

  •

  Apache License 2.0

  •2•4•0•0•Updated May 16, 2025May 16, 2025

• tensor-program-optimization-with-auto-batching

  Public
  Tensor Program Optimization with Auto-Batching (Master Thesis, ETH Zürich, 2025)

  inferenceloratvm+ 2peftllm

  Python

  •0•1•0•0•Updated Apr 8, 2025Apr 8, 2025

• llm-enhanced-entity-matching-comparative-analysis-of-traditional-and-modern-techniques

  Public
  LLM-Enhanced Entity Matching: Comparative Analysis of traditional and modern techniques (Master Thesis, ETH Zürich, 2025)

  entity-matchingllmcompound-ai-systems

  0•0•0•0•Updated Mar 27, 2025Mar 27, 2025

• understanding-gpu-architecture-implications-on-llm-serving-workloads

  Public
  Understanding GPU Architecture Implications on LLM Serving Workloads (Master Thesis, ETH Zürich, 2024)

  cudainferencepytorch+ 2transformerrocm

  Python

  •1•3•0•0•Updated Oct 24, 2024Oct 24, 2024

• FineInfer

  Public
  Deferred Continuous Batching in Resource-Efficient Large Language Model Serving (EuroMLSys 2024)

  inferencepytorchlora+ 4fine-tuningpeftllmco-serving

  Python

  •

  MIT License

  •2•17•0•0•Updated May 28, 2024May 28, 2024