eth-easl / cachew

Related projects ⓘ

Alternatives and complementary repositories for cachew

• WukLab / preble
  Stateful LLM Serving
  ☆38Updated 3 months ago
• suquark / ExoFlow
  A universal workflow system for exactly-once DAGs
  ☆23Updated last year
• msr-fiddle / CoorDL
  ☆23Updated last year
• SymbioticLab / Oobleck
  A resilient distributed training framework
  ☆85Updated 7 months ago
• msr-fiddle / CheckFreq
  ☆51Updated 3 years ago
• msr-fiddle / DS-Analyzer
  ☆35Updated 3 years ago
• danyangz / lightning
  Lightning In-Memory Object Store
  ☆44Updated 2 years ago
• rkhan055 / SHADE
  SHADE: Enable Fundamental Cacheability for Distributed Deep Learning Training
  ☆29Updated last year
• pkusys / Auncel
  Vector search with bounded performance.
  ☆33Updated 9 months ago
• pkusys / ElasticFlow
  Artifacts for our ASPLOS'23 paper ElasticFlow
  ☆52Updated 6 months ago
• saareliad / FTPipe
  FTPipe and related pipeline model parallelism research.
  ☆41Updated last year
• SJTU-IPADS / PhoenixOS
  Fast OS-level support for GPU checkpoint and restore
  ☆44Updated last week
• resource-disaggregation / jiffy
  Virtual Memory Abstraction for Serverless Architectures
  ☆45Updated 2 years ago
• suquark / hoplite
  ☆43Updated 3 years ago
• spcl / rFaaS
  rFaaS: a high-performance FaaS platform with RDMA acceleration for low-latency invocations.
  ☆49Updated last month
• Hsword / SpotServe
  SpotServe: Serving Generative Large Language Models on Preemptible Instances
  ☆101Updated 8 months ago
• uclasystem / bamboo
  Bamboo is a system for running large pipeline-parallel DNNs affordably, reliably, and efficiently using spot instances.
  ☆47Updated last year
• jasperzhong / swift
  ☆13Updated 2 years ago
• eth-easl / orion
  An interference-aware scheduler for fine-grained GPU sharing
  ☆111Updated 6 months ago
• casys-kaist / EnvPipe
  ☆23Updated last year
• msr-fiddle / harmony
  ☆16Updated last year
• SJTU-IPADS / disb
  DISB is a new DNN inference serving benchmark with diverse workloads and models, as well as real-world traces.
  ☆54Updated 3 months ago
• TankLabTJU / INFless
  The source code of INFless，a native serverless platform for AI inference.
  ☆35Updated 2 years ago
• DataManagementLab / RDMA_synchronization
  This is the source code for our (Tobias Ziegler, Jacob Nelson-Slivon, Carsten Binnig and Viktor Leis) published paper at SIGMOD’23: Desig…
  ☆21Updated last month
• msr-fiddle / synergy
  ☆48Updated last year
• thustorage / PetPS
  PetPS: Supporting Huge Embedding Models with Tiered Memory
  ☆29Updated 6 months ago
• cirquit / presto
  ☆13Updated last year
• csl-iisc / GPM-ASPLOS22
  ☆31Updated 5 months ago
• dywsjtu / apparate
  Code for "Apparate: Rethinking Early Exits to Tame Latency-Throughput Tensions in ML Serving" [SOSP '24]
  ☆16Updated last month