Alternatives and similar repositories for FlexKV

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

• antgroup / glake
  GLake: optimizing GPU memory management and IO transmission.
  ☆486Updated 7 months ago
• LLMServe / DistServe
  Disaggregated serving system for Large Language Models (LLMs).
  ☆709Updated 6 months ago
• AlibabaPAI / llumnix
  Efficient and easy multi-instance LLM serving
  ☆504Updated last month
• ai-dynamo / nixl
  NVIDIA Inference Xfer Library (NIXL)
  ☆688Updated this week
• volcengine / veScale
  A PyTorch Native LLM Training Framework
  ☆879Updated last month
• bytedance / InfiniStore
  KV cache store for distributed LLM inference
  ☆346Updated last month
• alibaba / rtp-llm
  RTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.
  ☆903Updated last week
• microsoft / msccl
  Microsoft Collective Communication Library
  ☆368Updated 2 years ago
• stepfun-ai / StepMesh
  ☆309Updated last month
• Tencent / KsanaLLM
  ☆508Updated last month
• bytedance / flux
  A fast communication-overlapping library for tensor/expert parallelism on GPUs.
  ☆1,153Updated 2 months ago
• ASISys / Adrenaline
  Injecting Adrenaline into LLM Serving: Boosting Resource Utilization and Throughput via Attention Disaggregation
  ☆37Updated last month
• atomicapple0 / libsmctrl
  Artifact from "Hardware Compute Partitioning on NVIDIA GPUs". THIS IS A FORK OF BAKITAS REPO. I AM NOT ONE OF THE AUTHORS OF THE PAPER.
  ☆38Updated last year
• NVIDIA / nccl-tests
  NCCL Tests
  ☆1,313Updated this week
• zartbot / shallowsim
  DeepSeek-V3/R1 inference performance simulator
  ☆170Updated 7 months ago
• LLMServe / SwiftTransformer
  High performance Transformer implementation in C++.
  ☆139Updated 9 months ago
• ByteDance-Seed / Triton-distributed
  Distributed Compiler based on Triton for Parallel Systems
  ☆1,206Updated 2 weeks ago
• sail-sg / zero-bubble-pipeline-parallelism
  Zero Bubble Pipeline Parallelism
  ☆433Updated 5 months ago
• alibaba / EasyParallelLibrary
  Easy Parallel Library (EPL) is a general and efficient deep learning framework for distributed model training.
  ☆269Updated 2 years ago
• byungsoo-oh / ml-systems-papers
  Curated collection of papers in machine learning systems
  ☆441Updated 3 weeks ago
• hahnyuan / LLM-Viewer
  Analyze the inference of Large Language Models (LLMs). Analyze aspects like computation, storage, transmission, and hardware roofline mod…
  ☆568Updated last year
• NVIDIA / nvbandwidth
  A tool for bandwidth measurements on NVIDIA GPUs.
  ☆553Updated 6 months ago
• microsoft / mscclpp
  MSCCL++: A GPU-driven communication stack for scalable AI applications
  ☆427Updated this week
• FlagOpen / FlagGems
  FlagGems is an operator library for large language models implemented in the Triton Language.
  ☆745Updated this week
• microsoft / vattention
  Dynamic Memory Management for Serving LLMs without PagedAttention
  ☆432Updated 5 months ago
• sgl-project / SpecForge
  Train speculative decoding models effortlessly and port them smoothly to SGLang serving.
  ☆451Updated this week
• Mellanox / nccl-rdma-sharp-plugins
  RDMA and SHARP plugins for nccl library
  ☆211Updated last week
• sgl-project / sgl-learning-materials
  Materials for learning SGLang
  ☆626Updated last week
• kwai / Megatron-Kwai
  [USENIX ATC '24] Accelerating the Training of Large Language Models using Efficient Activation Rematerialization and Optimal Hybrid Paral…
  ☆66Updated last year
• DicardoX / Research-Space
  This repository is established to store personal notes and annotated papers during daily research.
  ☆155Updated last month