Alternatives and similar repositories for papers

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

• microsoft / RetrievalAttention
  Scalable long-context LLM decoding that leverages sparsity—by treating the KV cache as a vector storage system.
  ☆81Updated last week
• hao-ai-lab / vllm-ltr
  [NeurIPS 2024] Efficient LLM Scheduling by Learning to Rank
  ☆59Updated 10 months ago
• microsoft / ParrotServe
  [OSDI'24] Serving LLM-based Applications Efficiently with Semantic Variable
  ☆183Updated last year
• amazon-science / piperag
  PipeRAG: Fast Retrieval-Augmented Generation via Algorithm-System Co-design (KDD 2025)
  ☆24Updated last year
• WukLab / preble
  Stateful LLM Serving
  ☆85Updated 6 months ago
• YaoJiayi / CacheBlend
  ☆137Updated 2 months ago
• hao-ai-lab / MuxServe
  ☆71Updated last year
• uclasystem / bamboo
  Bamboo is a system for running large pipeline-parallel DNNs affordably, reliably, and efficiently using spot instances.
  ☆51Updated 2 years ago
• ByteDance-Seed / StragglerAnalysis
  ☆42Updated 4 months ago
• alibaba / ServeGen
  A framework for generating realistic LLM serving workloads
  ☆63Updated 3 months ago
• SymbioticLab / Oobleck
  A resilient distributed training framework
  ☆95Updated last year
• NEO-MLSys25 / NEO
  NEO is a LLM inference engine built to save the GPU memory crisis by CPU offloading
  ☆62Updated 3 months ago
• alibaba-edu / qwen-bailian-usagetraces-anon
  ☆47Updated 3 months ago
• ovg-project / kvcached
  kvcached: Elastic KV cache for dynamic GPU sharing and efficient multi-LLM inference.
  ☆93Updated this week
• hongzhangblaze / CS854-F24
  ☆47Updated last week
• CentML / Mist
  [EuroSys'25] Mist: Efficient Distributed Training of Large Language Models via Memory-Parallelism Co-Optimization
  ☆17Updated last month
• Hsword / Awesome-Machine-Learning-System-Papers
  ☆77Updated 3 years ago
• HPMLL / BurstGPT
  A ChatGPT(GPT-3.5) & GPT-4 Workload Trace to Optimize LLM Serving Systems
  ☆205Updated 2 months ago
• awslabs / optimizing-multitask-training-through-dynamic-pipelines
  Official repository for the paper DynaPipe: Optimizing Multi-task Training through Dynamic Pipelines
  ☆20Updated last year
• HugoZHL / PQCache
  [SIGMOD 2025] PQCache: Product Quantization-based KVCache for Long Context LLM Inference
  ☆71Updated 3 months ago
• Raphael-Hao / brainstorm
  Compiler for Dynamic Neural Networks
  ☆46Updated last year
• rkhan055 / SHADE
  SHADE: Enable Fundamental Cacheability for Distributed Deep Learning Training
  ☆35Updated 2 years ago
• kvcache-ai / TrEnv-X
  ☆54Updated last week
• Hsword / SpotServe
  SpotServe: Serving Generative Large Language Models on Preemptible Instances
  ☆129Updated last year
• xinhao-luo / ClusterFusion
  [NeurIPS 2025] ClusterFusion: Expanding Operator Fusion Scope for LLM Inference via Cluster-Level Collective Primitive
  ☆18Updated last week
• dywsjtu / apparate
  Artifact for "Apparate: Rethinking Early Exits to Tame Latency-Throughput Tensions in ML Serving" [SOSP '24]
  ☆25Updated 10 months ago
• Multi-LLM / prism-research
  Research prototype of PRISM — a cost-efficient multi-LLM serving system with flexible time- and space-based GPU sharing.
  ☆27Updated last month
• thustorage / Medusa
  Medusa: Accelerating Serverless LLM Inference with Materialization [ASPLOS'25]
  ☆30Updated 4 months ago
• LoongServe / LoongServe
  ☆123Updated 10 months ago
• Thesys-lab / Helix-ASPLOS25
  Open-source implementation for "Helix: Serving Large Language Models over Heterogeneous GPUs and Network via Max-Flow"
  ☆67Updated 10 months ago