Alternatives and similar repositories for flexflow-serve

Users that are interested in flexflow-serve are comparing it to the libraries listed below

• infinigence / FlashOverlap
  A lightweight design for computation-communication overlap.
  ☆146Updated 3 weeks ago
• LLMServe / SwiftTransformer
  High performance Transformer implementation in C++.
  ☆125Updated 5 months ago
• WukLab / preble
  Stateful LLM Serving
  ☆73Updated 4 months ago
• LoongServe / LoongServe
  ☆106Updated 8 months ago
• hao-ai-lab / MuxServe
  ☆64Updated last year
• DD-DuDa / BitDecoding
  A GPU-optimized system for efficient long-context LLMs decoding with low-bit KV cache.
  ☆51Updated last month
• microsoft / nnscaler
  nnScaler: Compiling DNN models for Parallel Training
  ☆113Updated this week
• alibaba / llm-scheduling-artifact
  Artifact of OSDI '24 paper, ”Llumnix: Dynamic Scheduling for Large Language Model Serving“
  ☆61Updated last year
• alibaba / easydist
  Automated Parallelization System and Infrastructure for Multiple Ecosystems
  ☆79Updated 7 months ago
• flashinfer-ai / cutlass-viz
  ☆60Updated 2 months ago
• infinigence / Semi-PD
  A prefill & decode disaggregated LLM serving framework with shared GPU memory and fine-grained compute isolation.
  ☆93Updated last month
• zartbot / shallowsim
  DeepSeek-V3/R1 inference performance simulator
  ☆154Updated 3 months ago
• yifuwang / symm-mem-recipes
  ☆94Updated 6 months ago
• parasailteam / coconet
  ☆79Updated 2 years ago
• shenh10 / DeepSeek_Simulator
  ☆79Updated 3 months ago
• ademeure / DeeperGEMM
  DeeperGEMM: crazy optimized version
  ☆69Updated 2 months ago
• AlibabaResearch / flash-llm
  Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity
  ☆216Updated last year
• TiledTensor / TiledCUDA
  We invite you to visit and follow our new repository at https://github.com/microsoft/TileFusion. TiledCUDA is a highly efficient kernel …
  ☆183Updated 5 months ago
• microsoft / ParrotServe
  [OSDI'24] Serving LLM-based Applications Efficiently with Semantic Variable
  ☆167Updated 9 months ago
• eth-easl / orion
  An interference-aware scheduler for fine-grained GPU sharing
  ☆141Updated 5 months ago
• eniac / paella
  Paella: Low-latency Model Serving with Virtualized GPU Scheduling
  ☆59Updated last year
• uccl-project / uccl
  Ultra and Unified CCL
  ☆390Updated this week
• HPMLL / NVIDIA-Hopper-Benchmark
  ☆49Updated last month
• ParCIS / Chimera
  Chimera: bidirectional pipeline parallelism for efficiently training large-scale models.
  ☆67Updated 3 months ago
• awslabs / optimizing-multitask-training-through-dynamic-pipelines
  Official repository for the paper DynaPipe: Optimizing Multi-task Training through Dynamic Pipelines
  ☆19Updated last year
• Infrawaves / DeepEP_ibrc_dual-ports_multiQP
  Aims to implement dual-port and multi-qp solutions in deepEP ibrc transport
  ☆53Updated 2 months ago
• EfficientMoE / MoE-Infinity
  PyTorch library for cost-effective, fast and easy serving of MoE models.
  ☆207Updated this week
• triton-lang / kernels
  ☆83Updated 8 months ago
• CalebDu / Awesome-Cute
  ☆82Updated last month
• mcrl / tccl
  Thunder Research Group's Collective Communication Library
  ☆38Updated this week