Alternatives and similar repositories for gLLM

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

• KuangjuX / NVSHMEM-Tutorial
  NVSHMEM‑Tutorial: Build a DeepEP‑like GPU Buffer
  ☆128Updated this week
• tile-ai / tilescale
  Tile-based language built for AI computation across all scales
  ☆57Updated last week
• HPMLL / NVIDIA-Hopper-Benchmark
  ☆57Updated 3 months ago
• DeepLink-org / DLSlime
  DLSlime: Flexible & Efficient Heterogeneous Transfer Toolkit
  ☆62Updated this week
• infinigence / FlashOverlap
  A lightweight design for computation-communication overlap.
  ☆167Updated last week
• LLMServe / SwiftTransformer
  High performance Transformer implementation in C++.
  ☆132Updated 8 months ago
• shenh10 / DeepSeek_Simulator
  ☆85Updated 5 months ago
• Chtholly-Boss / swizzle
  A practical way of learning Swizzle
  ☆27Updated 7 months ago
• Ascend / triton-ascend
  Triton adapter for Ascend. Mirror of https://gitee.com/ascend/triton-ascend
  ☆71Updated this week
• yuyangJin / PerFlow-AI
  PerFlow-AI is a programmable performance analysis, modeling, prediction tool for AI system.
  ☆24Updated this week
• CalebDu / Awesome-Cute
  ☆104Updated 4 months ago
• flashinfer-ai / cutlass-viz
  ☆64Updated 4 months ago
• LoongServe / LoongServe
  ☆123Updated 10 months ago
• WukLab / preble
  Stateful LLM Serving
  ☆84Updated 6 months ago
• ademeure / DeeperGEMM
  DeeperGEMM: crazy optimized version
  ☆70Updated 4 months ago
• ovg-project / kvcached
  kvcached: Elastic KV cache for dynamic GPU sharing and efficient multi-LLM inference.
  ☆91Updated this week
• wu-kan / wuk_cupti_wrapper
  a simple API to use CUPTI
  ☆11Updated last month
• cherichy / tilecute
  ☆30Updated 2 months ago
• flexflow / flexflow-serve
  FlexFlow Serve: Low-Latency, High-Performance LLM Serving
  ☆57Updated last week
• tsinghua-ideal / Canvas
  Canvas: End-to-End Kernel Architecture Search in Neural Networks
  ☆27Updated 10 months ago
• DD-DuDa / BitDecoding
  A GPU-optimized system for efficient long-context LLMs decoding with low-bit KV cache.
  ☆59Updated 3 weeks ago
• antgroup / DeepXTrace
  DeepXTrace is a lightweight tool for precisely diagnosing slow ranks in DeepEP-based environments.
  ☆51Updated this week
• thunlp / Seq1F1B
  Sequence-level 1F1B schedule for LLMs.
  ☆32Updated 3 weeks ago
• AlibabaPAI / FLASHNN
  ☆98Updated last year
• hao-ai-lab / MuxServe
  ☆71Updated last year
• rchardx / cuda-gemm
  ☆28Updated 5 months ago
• heheda12345 / MagPy
  ☆39Updated last year
• google / iopddl
  Supplemental materials for The ASPLOS 2025 / EuroSys 2025 Contest on Intra-Operator Parallelism for Distributed Deep Learning
  ☆23Updated 4 months ago
• Hsword / Awesome-Machine-Learning-System-Papers
  ☆76Updated 3 years ago
• Raphael-Hao / brainstorm
  Compiler for Dynamic Neural Networks
  ☆46Updated last year