Alternatives and similar repositories for datastates-llm

Users that are interested in datastates-llm are comparing it to the libraries listed below

• SymbioticLab / Oobleck
  A resilient distributed training framework
  ☆95Updated last year
• kungfu-team / tenplex
  Dynamic resources changes for multi-dimensional parallelism training
  ☆25Updated 7 months ago
• ByteDance-Seed / StragglerAnalysis
  ☆31Updated last month
• casys-kaist / EnvPipe
  ☆25Updated last year
• WukLab / preble
  Stateful LLM Serving
  ☆73Updated 3 months ago
• thu-pacman / FasterMoE
  ☆84Updated 3 years ago
• msr-fiddle / CheckFreq
  ☆53Updated 4 years ago
• hao-ai-lab / MuxServe
  ☆62Updated last year
• osayamenja / Kleos
  Complete GPU residency for ML.
  ☆17Updated last week
• NEO-MLSys25 / NEO
  NEO is a LLM inference engine built to save the GPU memory crisis by CPU offloading
  ☆39Updated last week
• eth-easl / orion
  An interference-aware scheduler for fine-grained GPU sharing
  ☆140Updated 5 months ago
• msr-fiddle / harmony
  ☆16Updated 2 years ago
• alibaba / llm-scheduling-artifact
  Artifact of OSDI '24 paper, ”Llumnix: Dynamic Scheduling for Large Language Model Serving“
  ☆61Updated last year
• cirquit / presto
  ☆15Updated 2 years ago
• LoongServe / LoongServe
  ☆104Updated 7 months ago
• ParCIS / Chimera
  Chimera: bidirectional pipeline parallelism for efficiently training large-scale models.
  ☆67Updated 3 months ago
• Relaxed-System-Lab / HexGen
  [ICML 2024] Serving LLMs on heterogeneous decentralized clusters.
  ☆26Updated last year
• infinigence / FlashOverlap
  A lightweight design for computation-communication overlap.
  ☆143Updated last week
• jasperzhong / swift
  ☆14Updated 3 years ago
• SJTU-IPADS / disb
  DISB is a new DNN inference serving benchmark with diverse workloads and models, as well as real-world traces.
  ☆52Updated 10 months ago
• Ying1123 / VTC-artifact
  ☆32Updated last year
• zhuohan123 / terapipe
  ☆74Updated 4 years ago
• awslabs / optimizing-multitask-training-through-dynamic-pipelines
  Official repository for the paper DynaPipe: Optimizing Multi-task Training through Dynamic Pipelines
  ☆19Updated last year
• LighT-chenml / LightCheck
  ☆9Updated last year
• msr-fiddle / blox
  ☆44Updated 11 months ago
• microsoft / RetrievalAttention
  Scalable long-context LLM decoding that leverages sparsity—by treating the KV cache as a vector storage system.
  ☆54Updated last week
• dywsjtu / apparate
  Artifact for "Apparate: Rethinking Early Exits to Tame Latency-Throughput Tensions in ML Serving" [SOSP '24]
  ☆25Updated 7 months ago
• msr-fiddle / CoorDL
  ☆24Updated 2 years ago
• zhengzangw / Sequence-Scheduling
  PyTorch implementation of paper "Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipeline".
  ☆88Updated 2 years ago
• DachengLi1 / AMP
  (NeurIPS 2022) Automatically finding good model-parallel strategies, especially for complex models and clusters.
  ☆39Updated 2 years ago