Alternatives and similar repositories for cachew:

Users that are interested in cachew are comparing it to the libraries listed below

• suquark / hoplite
  ☆44Updated 3 years ago
• msr-fiddle / CoorDL
  ☆24Updated last year
• msr-fiddle / CheckFreq
  ☆53Updated 4 years ago
• saareliad / FTPipe
  FTPipe and related pipeline model parallelism research.
  ☆41Updated last year
• danyangz / lightning
  Lightning In-Memory Object Store
  ☆45Updated 3 years ago
• pkusys / Auncel
  Vector search with bounded performance.
  ☆34Updated last year
• WukLab / preble
  Stateful LLM Serving
  ☆63Updated last month
• SymbioticLab / Oobleck
  A resilient distributed training framework
  ☆94Updated last year
• msr-fiddle / DS-Analyzer
  ☆35Updated 4 years ago
• Hsword / SpotServe
  SpotServe: Serving Generative Large Language Models on Preemptible Instances
  ☆113Updated last year
• uccl-project / uccl
  Ultra | Ultimate | Unified CCL
  ☆58Updated 2 months ago
• rkhan055 / SHADE
  SHADE: Enable Fundamental Cacheability for Distributed Deep Learning Training
  ☆31Updated 2 years ago
• thustorage / Medusa
  Medusa: Accelerating Serverless LLM Inference with Materialization [ASPLOS'25]
  ☆22Updated 4 months ago
• quiver-team / quiver-feature
  High performance RDMA-based distributed feature collection component for training GNN model on EXTREMELY large graph
  ☆52Updated 2 years ago
• casys-kaist / EnvPipe
  ☆24Updated last year
• dywsjtu / apparate
  Artifact for "Apparate: Rethinking Early Exits to Tame Latency-Throughput Tensions in ML Serving" [SOSP '24]
  ☆23Updated 4 months ago
• netx-repo / PipeSwitch
  PipeSwitch: Fast Pipelined Context Switching for Deep Learning Applications
  ☆126Updated 2 years ago
• msr-fiddle / harmony
  ☆16Updated 2 years ago
• microsoft / SuperScaler
  An experimental parallel training platform
  ☆54Updated last year
• stanford-mast / INFaaS
  Model-less Inference Serving
  ☆88Updated last year
• pkusys / ElasticFlow
  Artifacts for our ASPLOS'23 paper ElasticFlow
  ☆51Updated 11 months ago
• jasperzhong / swift
  ☆14Updated 2 years ago
• eth-easl / orion
  An interference-aware scheduler for fine-grained GPU sharing
  ☆130Updated 2 months ago
• facebookresearch / param
  PArametrized Recommendation and Ai Model benchmark is a repository for development of numerous uBenchmarks as well as end to end nets for…
  ☆134Updated this week
• uclasystem / bamboo
  Bamboo is a system for running large pipeline-parallel DNNs affordably, reliably, and efficiently using spot instances.
  ☆49Updated 2 years ago
• hao-ai-lab / MuxServe
  ☆59Updated 10 months ago
• tyler-griggs / melange-release
  ☆45Updated 9 months ago
• suquark / ExoFlow
  A universal workflow system for exactly-once DAGs
  ☆23Updated last year
• SJTU-IPADS / disb
  DISB is a new DNN inference serving benchmark with diverse workloads and models, as well as real-world traces.
  ☆52Updated 7 months ago
• SymbioticLab / Salus
  Fine-grained GPU sharing primitives
  ☆141Updated 5 years ago