Alternatives and similar repositories for Cost-Model-papers

Users that are interested in Cost-Model-papers are comparing it to the libraries listed below

• jasperzhong / swift
  ☆15Updated 3 years ago
• thustorage / Medusa
  Medusa: Accelerating Serverless LLM Inference with Materialization [ASPLOS'25]
  ☆40Updated 7 months ago
• uw-mad-dash / shockwave
  Artifact for "Shockwave: Fair and Efficient Cluster Scheduling for Dynamic Adaptation in Machine Learning" [NSDI '23]
  ☆46Updated 3 years ago
• S-Lab-System-Group / Awesome-ML-for-System
  SOTA Learning-augmented Systems
  ☆37Updated 3 years ago
• harvard-cns / Harvard-CNS-Seminar
  Reading seminar in Harvard Cloud Networking and Systems Group
  ☆16Updated 3 years ago
• SJTU-IPADS / reef-artifacts
  A GPU-accelerated DNN inference serving system that supports instant kernel preemption and biased concurrent execution in GPU scheduling.
  ☆44Updated 3 years ago
• SJTU-IPADS / disb
  DISB is a new DNN inference serving benchmark with diverse workloads and models, as well as real-world traces.
  ☆57Updated last year
• gudiandian / ElasticFlow
  ☆16Updated last year
• rkhan055 / SHADE
  SHADE: Enable Fundamental Cacheability for Distributed Deep Learning Training
  ☆35Updated 2 years ago
• uclasystem / bamboo
  Bamboo is a system for running large pipeline-parallel DNNs affordably, reliably, and efficiently using spot instances.
  ☆54Updated 3 years ago
• msr-fiddle / CheckFreq
  ☆56Updated 4 years ago
• kvcache-ai / TrEnv-X
  ☆69Updated 3 months ago
• msr-fiddle / harmony
  ☆17Updated 3 years ago
• alibaba / llm-scheduling-artifact
  Artifact of OSDI '24 paper, ”Llumnix: Dynamic Scheduling for Large Language Model Serving“
  ☆64Updated last year
• suquark / hoplite
  ☆44Updated 4 years ago
• alibaba-edu / qwen-bailian-usagetraces-anon
  ☆63Updated last month
• netx-repo / PipeSwitch
  PipeSwitch: Fast Pipelined Context Switching for Deep Learning Applications
  ☆126Updated 3 years ago
• csl-iisc / GPM-ASPLOS22
  ☆36Updated last year
• dywsjtu / apparate
  Artifact for "Apparate: Rethinking Early Exits to Tame Latency-Throughput Tensions in ML Serving" [SOSP '24]
  ☆25Updated last year
• SJTU-IPADS / reef
  REEF is a GPU-accelerated DNN inference serving system that enables instant kernel preemption and biased concurrent execution in GPU sche…
  ☆102Updated 2 years ago
• pkusys / Auncel
  Vector search with bounded performance.
  ☆35Updated last year
• uclasystem / dorylus
  Dorylus: Affordable, Scalable, and Accurate GNN Training
  ☆76Updated 4 years ago
• Trinity-data-store / Trinity
  EuroSys '24: "Trinity: A Fast Compressed Multi-attribute Data Store"
  ☆19Updated 9 months ago
• liangyuRain / ForestColl
  ☆15Updated 7 months ago
• thustorage / PetPS
  PetPS: Supporting Huge Embedding Models with Tiered Memory
  ☆33Updated last year
• Hsword / Awesome-Machine-Learning-System-Papers
  ☆79Updated 3 years ago
• SJTU-IPADS / fgnn-artifacts
  FGNN's artifact evaluation (EuroSys 2022)
  ☆17Updated 3 years ago
• alpa-projects / mms
  AlpaServe: Statistical Multiplexing with Model Parallelism for Deep Learning Serving (OSDI 23)
  ☆92Updated 2 years ago
• Multi-LLM / prism-research
  Research prototype of PRISM — a cost-efficient multi-LLM serving system with flexible time- and space-based GPU sharing.
  ☆49Updated 4 months ago
• quiver-team / quiver-feature
  High performance RDMA-based distributed feature collection component for training GNN model on EXTREMELY large graph
  ☆57Updated 3 years ago