Alternatives and similar repositories for hotline

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

• parasailteam / coconet
  ☆84Updated 3 years ago
• eniac / paella
  Paella: Low-latency Model Serving with Virtualized GPU Scheduling
  ☆68Updated last year
• ConnollyLeon / awesome-Auto-Parallelism
  A baseline repository of Auto-Parallelism in Training Neural Networks
  ☆147Updated 3 years ago
• zhuohan123 / terapipe
  ☆77Updated 4 years ago
• thu-pacman / PET
  PET: Optimizing Tensor Programs with Partially Equivalent Transformations and Automated Corrections
  ☆125Updated 3 years ago
• Linestro / GRACE
  Artifact of ASPLOS'23 paper entitled: GRACE: A Scalable Graph-Based Approach to Accelerating Recommendation Model Inference
  ☆19Updated 2 years ago
• S-Lab-System-Group / Awesome-ML-for-System
  SOTA Learning-augmented Systems
  ☆37Updated 3 years ago
• yuyangJin / PerFlow-AI
  PerFlow-AI is a programmable performance analysis, modeling, prediction tool for AI system.
  ☆28Updated last week
• alpa-projects / mms
  AlpaServe: Statistical Multiplexing with Model Parallelism for Deep Learning Serving (OSDI 23)
  ☆93Updated 2 years ago
• Raphael-Hao / brainstorm
  Compiler for Dynamic Neural Networks
  ☆45Updated 2 years ago
• nox-410 / tvm.tl
  An extention of TVMScript to write simple and high performance GPU kernels with tensorcore.
  ☆51Updated last year
• alibaba / llm-scheduling-artifact
  Artifact of OSDI '24 paper, ”Llumnix: Dynamic Scheduling for Large Language Model Serving“
  ☆64Updated last year
• AlibabaPAI / DAPPLE
  An Efficient Pipelined Data Parallel Approach for Training Large Model
  ☆76Updated 5 years ago
• saareliad / FTPipe
  FTPipe and related pipeline model parallelism research.
  ☆44Updated 2 years ago
• BaguaSys / bagua-net
  High performance NCCL plugin for Bagua.
  ☆15Updated 4 years ago
• KuangjuX / NVSHMEM-Tutorial
  NVSHMEM‑Tutorial: Build a DeepEP‑like GPU Buffer
  ☆161Updated 4 months ago
• DachengLi1 / AMP
  (NeurIPS 2022) Automatically finding good model-parallel strategies, especially for complex models and clusters.
  ☆44Updated 3 years ago
• alibaba / easydist
  Automated Parallelization System and Infrastructure for Multiple Ecosystems
  ☆82Updated last year
• tlc-pack / cutlass_fpA_intB_gemm
  A standalone GEMM kernel for fp16 activation and quantized weight, extracted from FasterTransformer
  ☆96Updated 4 months ago
• microsoft / SuperScaler
  An experimental parallel training platform
  ☆56Updated last year
• UofT-EcoSystem / DietCode
  DietCode Code Release
  ☆65Updated 3 years ago
• netx-repo / PipeSwitch
  PipeSwitch: Fast Pipelined Context Switching for Deep Learning Applications
  ☆127Updated 3 years ago
• yalue / cuda_scheduling_examiner_mirror
  A tool for examining GPU scheduling behavior.
  ☆92Updated last year
• Sys-KU / DeepPlan
  [ACM EuroSys 2023] Fast and Efficient Model Serving Using Multi-GPUs with Direct-Host-Access
  ☆56Updated 6 months ago
• alibaba / TePDist
  TePDist (TEnsor Program DISTributed) is an HLO-level automatic distributed system for DL models.
  ☆99Updated 2 years ago
• infinigence / Semi-PD
  A prefill & decode disaggregated LLM serving framework with shared GPU memory and fine-grained compute isolation.
  ☆123Updated last month
• LeiWang1999 / tvm_gpu_gemm
  play gemm with tvm
  ☆92Updated 2 years ago
• yifuwang / symm-mem-recipes
  ☆159Updated last year
• SJTU-IPADS / disb
  DISB is a new DNN inference serving benchmark with diverse workloads and models, as well as real-world traces.
  ☆58Updated last year
• gfvvz / triton-learning-materials
  Triton Compiler related materials.
  ☆42Updated last year