Alternatives and similar repositories for Medusa

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

• alibaba-edu / qwen-bailian-usagetraces-anon
  ☆39Updated last month
• Thesys-lab / Helix-ASPLOS25
  Open-source implementation for "Helix: Serving Large Language Models over Heterogeneous GPUs and Network via Max-Flow"
  ☆58Updated 8 months ago
• LLMServe / dLoRA-artifact
  ☆24Updated last year
• uclasystem / bamboo
  Bamboo is a system for running large pipeline-parallel DNNs affordably, reliably, and efficiently using spot instances.
  ☆50Updated 2 years ago
• alibaba / llm-scheduling-artifact
  Artifact of OSDI '24 paper, ”Llumnix: Dynamic Scheduling for Large Language Model Serving“
  ☆62Updated last year
• ovg-project / kvcached
  kvcached: Elastic KV cache for dynamic GPU sharing and efficient multi-LLM inference.
  ☆35Updated last week
• gudiandian / ElasticFlow
  ☆16Updated last year
• thustorage / PetPS
  PetPS: Supporting Huge Embedding Models with Tiered Memory
  ☆32Updated last year
• pkusys / ElasticFlow
  Artifacts for our ASPLOS'23 paper ElasticFlow
  ☆52Updated 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…
  ☆96Updated 2 years ago
• XpuOS / xsched
  A preemptive scheduling framework for diverse XPUs, including GPUs, NPUs, ASICs, and FPGAs
  ☆74Updated last week
• csl-iisc / GPM-ASPLOS22
  ☆36Updated last year
• rkhan055 / SHADE
  SHADE: Enable Fundamental Cacheability for Distributed Deep Learning Training
  ☆35Updated 2 years ago
• alpa-projects / mms
  AlpaServe: Statistical Multiplexing with Model Parallelism for Deep Learning Serving (OSDI 23)
  ☆83Updated 2 years ago
• SJTU-IPADS / ugache
  ☆22Updated last year
• NEO-MLSys25 / NEO
  NEO is a LLM inference engine built to save the GPU memory crisis by CPU offloading
  ☆49Updated last month
• dmemsys / Aceso
  This is the implementation repository of our SOSP'24 paper: Aceso: Achieving Efficient Fault Tolerance in Memory-Disaggregated Key-Value …
  ☆21Updated 9 months ago
• uw-mad-dash / shockwave
  Artifact for "Shockwave: Fair and Efficient Cluster Scheduling for Dynamic Adaptation in Machine Learning" [NSDI '23]
  ☆44Updated 2 years ago
• WukLab / Mira
  A Progam-Behavior-Guided Far Memory System
  ☆35Updated last year
• Hsword / Awesome-Machine-Learning-System-Papers
  ☆74Updated 3 years ago
• dywsjtu / apparate
  Artifact for "Apparate: Rethinking Early Exits to Tame Latency-Throughput Tensions in ML Serving" [SOSP '24]
  ☆25Updated 8 months ago
• SJTU-IPADS / reef-artifacts
  A GPU-accelerated DNN inference serving system that supports instant kernel preemption and biased concurrent execution in GPU scheduling.
  ☆42Updated 3 years ago
• WukLab / preble
  Stateful LLM Serving
  ☆77Updated 4 months ago
• msr-fiddle / CheckFreq
  ☆55Updated 4 years ago
• minghust / motor
  [OSDI 2024] Motor: Enabling Multi-Versioning for Distributed Transactions on Disaggregated Memory
  ☆49Updated last year
• HPMLL / BurstGPT
  A ChatGPT(GPT-3.5) & GPT-4 Workload Trace to Optimize LLM Serving Systems
  ☆190Updated last week
• ruipeterpan / marconi
  Artifact for "Marconi: Prefix Caching for the Era of Hybrid LLMs" [MLSys '25 Outstanding Paper Award, Honorable Mention]
  ☆15Updated 5 months ago
• James-QiuHaoran / LLM-serving-with-proxy-models
  Efficient Interactive LLM Serving with Proxy Model-based Sequence Length Prediction | A tiny BERT model can tell you the verbosity of an …
  ☆38Updated last year
• Raphael-Hao / brainstorm
  Compiler for Dynamic Neural Networks
  ☆46Updated last year
• hongzhangblaze / CS854-F24
  ☆42Updated this week