Alternatives and similar repositories for SpaceServe

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

• DeepLink-org / DLSlime
  DLSlime: Flexible & Efficient Heterogeneous Transfer Toolkit
  ☆92Updated last week
• KuangjuX / NVSHMEM-Tutorial
  NVSHMEM‑Tutorial: Build a DeepEP‑like GPU Buffer
  ☆158Updated 4 months ago
• Infrawaves / DeepEP_ibrc_dual-ports_multiQP
  Aims to implement dual-port and multi-qp solutions in deepEP ibrc transport
  ☆73Updated 8 months ago
• alibaba / llm-scheduling-artifact
  Artifact of OSDI '24 paper, ”Llumnix: Dynamic Scheduling for Large Language Model Serving“
  ☆64Updated last year
• kvcache-ai / TrEnv-X
  ☆73Updated 4 months ago
• microsoft / tokenweave
  Accepted to MLSys 2026
  ☆70Updated this week
• ademeure / DeeperGEMM
  DeeperGEMM: crazy optimized version
  ☆73Updated 8 months ago
• infinigence / Semi-PD
  A prefill & decode disaggregated LLM serving framework with shared GPU memory and fine-grained compute isolation.
  ☆123Updated last month
• flashinfer-ai / debug-print
  Debug print operator for cudagraph debugging
  ☆14Updated last year
• infinigence / FUSCO
  High-performance distributed data shuffling (all-to-all) library for MoE training and inference
  ☆109Updated last month
• infinigence / HamiltonAttention
  ☆41Updated 3 months ago
• NEO-MLSys25 / NEO
  NEO is a LLM inference engine built to save the GPU memory crisis by CPU offloading
  ☆81Updated 7 months ago
• alibaba-edu / qwen-bailian-usagetraces-anon
  ☆78Updated last week
• flashinfer-ai / cutlass-viz
  ☆65Updated 9 months ago
• liangyuRain / ForestColl
  ☆16Updated 9 months ago
• Azure / msccl-executor-nccl
  ☆47Updated last year
• LLMServe / SwiftTransformer
  High performance Transformer implementation in C++.
  ☆148Updated last year
• WukLab / preble
  Stateful LLM Serving
  ☆95Updated 10 months ago
• abcdabcd987 / libfabric-efa-demo
  ☆76Updated last year
• antgroup / DeepXTrace
  DeepXTrace is a lightweight tool for precisely diagnosing slow ranks in DeepEP-based environments.
  ☆91Updated 2 weeks ago
• infinigence / FlashOverlap
  A lightweight design for computation-communication overlap.
  ☆219Updated 2 weeks ago
• zhuzilin / flash-attention-with-sink
  ☆38Updated 5 months ago
• dywsjtu / apparate
  Artifact for "Apparate: Rethinking Early Exits to Tame Latency-Throughput Tensions in ML Serving" [SOSP '24]
  ☆25Updated last year
• thustorage / Medusa
  Medusa: Accelerating Serverless LLM Inference with Materialization [ASPLOS'25]
  ☆41Updated 8 months ago
• inclusionAI / asystem-amem
  A NCCL extension library, designed to efficiently offload GPU memory allocated by the NCCL communication library.
  ☆87Updated last month
• microsoft / RetrievalAttention
  Scalable long-context LLM decoding that leverages sparsity—by treating the KV cache as a vector storage system.
  ☆119Updated last month
• alibaba / ServeGen
  A framework for generating realistic LLM serving workloads
  ☆99Updated 3 months ago
• S-Lab-System-Group / Awesome-ML-for-System
  SOTA Learning-augmented Systems
  ☆37Updated 3 years ago
• hao-ai-lab / MuxServe
  ☆84Updated 3 months ago
• sii-research / VCCL
  Venus Collective Communication Library, supported by SII and Infrawaves.
  ☆137Updated this week