Alternatives and similar repositories for ForestColl

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

• thustorage / Medusa
  Medusa: Accelerating Serverless LLM Inference with Materialization [ASPLOS'25]
  ☆28Updated 2 months ago
• alibaba-edu / qwen-bailian-usagetraces-anon
  ☆39Updated 2 months ago
• microsoft / taccl
  TACCL: Guiding Collective Algorithm Synthesis using Communication Sketches
  ☆74Updated 2 years ago
• Thesys-lab / Helix-ASPLOS25
  Open-source implementation for "Helix: Serving Large Language Models over Heterogeneous GPUs and Network via Max-Flow"
  ☆59Updated 8 months ago
• suquark / hoplite
  ☆44Updated 3 years ago
• SJTU-IPADS / reef
  REEF is a GPU-accelerated DNN inference serving system that enables instant kernel preemption and biased concurrent execution in GPU sche…
  ☆98Updated 2 years ago
• microsoft / TE-CCL
  ☆37Updated 11 months ago
• H-Huang / torch_collective_extension
  A minimum demo for PyTorch distributed extension functionality for collectives.
  ☆13Updated 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
• jasperzhong / swift
  ☆15Updated 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
• axio-project / FuseLink
  Efficient GPU communication over multiple NICs.
  ☆16Updated 2 weeks ago
• JF-D / Proteus
  ☆23Updated last year
• mutinifni / splitwise-sim
  LLM serving cluster simulator
  ☆108Updated last year
• 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
• alpa-projects / mms
  AlpaServe: Statistical Multiplexing with Model Parallelism for Deep Learning Serving (OSDI 23)
  ☆84Updated 2 years ago
• alibaba / llm-scheduling-artifact
  Artifact of OSDI '24 paper, ”Llumnix: Dynamic Scheduling for Large Language Model Serving“
  ☆62Updated last year
• LLMServe / dLoRA-artifact
  ☆24Updated last year
• Rivendile / Muri
  Artifacts for our SIGCOMM'22 paper Muri
  ☆41Updated last year
• gudiandian / ElasticFlow
  ☆16Updated last year
• msr-fiddle / CheckFreq
  ☆55Updated 4 years 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
• casys-kaist / glet
  ☆49Updated 7 months ago
• msr-fiddle / blox
  ☆44Updated last year
• Raphael-Hao / brainstorm
  Compiler for Dynamic Neural Networks
  ☆46Updated last year
• Nu-NSDI23 / Nu
  Nu is a new datacenter system that enables developers to build fungible applications that can use datacenter resources wherever they are.
  ☆38Updated last year
• 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 …
  ☆39Updated last year
• casys-kaist / EnvPipe
  ☆25Updated last year
• NEO-MLSys25 / NEO
  NEO is a LLM inference engine built to save the GPU memory crisis by CPU offloading
  ☆50Updated last month
• rkhan055 / SHADE
  SHADE: Enable Fundamental Cacheability for Distributed Deep Learning Training
  ☆35Updated 2 years ago