Alternatives and similar repositories for veScale

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

• LLMServe / DistServe
  Disaggregated serving system for Large Language Models (LLMs).
  ☆737Updated 8 months ago
• ByteDance-Seed / Triton-distributed
  Distributed Compiler based on Triton for Parallel Systems
  ☆1,260Updated 2 weeks ago
• bytedance / flux
  A fast communication-overlapping library for tensor/expert parallelism on GPUs.
  ☆1,182Updated 3 months ago
• sail-sg / zero-bubble-pipeline-parallelism
  Zero Bubble Pipeline Parallelism
  ☆437Updated 6 months ago
• efeslab / Nanoflow
  A throughput-oriented high-performance serving framework for LLMs
  ☆918Updated last month
• sgl-project / sgl-learning-materials
  Materials for learning SGLang
  ☆658Updated 2 weeks ago
• AlibabaPAI / llumnix
  Efficient and easy multi-instance LLM serving
  ☆512Updated 3 months ago
• antgroup / glake
  GLake: optimizing GPU memory management and IO transmission.
  ☆490Updated 8 months ago
• sgl-project / SpecForge
  Train speculative decoding models effortlessly and port them smoothly to SGLang serving.
  ☆523Updated this week
• zhuzilin / ring-flash-attention
  Ring attention implementation with flash attention
  ☆923Updated 2 months ago
• alibaba / rtp-llm
  RTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.
  ☆934Updated this week
• ai-dynamo / nixl
  NVIDIA Inference Xfer Library (NIXL)
  ☆740Updated this week
• hahnyuan / LLM-Viewer
  Analyze the inference of Large Language Models (LLMs). Analyze aspects like computation, storage, transmission, and hardware roofline mod…
  ☆589Updated last year
• perplexityai / pplx-kernels
  Perplexity GPU Kernels
  ☆534Updated 3 weeks ago
• feifeibear / long-context-attention
  USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference
  ☆605Updated last month
• cli99 / llm-analysis
  Latency and Memory Analysis of Transformer Models for Training and Inference
  ☆466Updated 7 months ago
• microsoft / vattention
  Dynamic Memory Management for Serving LLMs without PagedAttention
  ☆446Updated 6 months ago
• microsoft / sarathi-serve
  A low-latency & high-throughput serving engine for LLMs
  ☆450Updated last month
• flagos-ai / FlagScale
  FlagScale is a large model toolkit based on open-sourced projects.
  ☆416Updated last week
• ByteDance-Seed / ByteCheckpoint
  ByteCheckpoint: An Unified Checkpointing Library for LFMs
  ☆254Updated this week
• microsoft / vidur
  A large-scale simulation framework for LLM inference
  ☆488Updated 4 months ago
• flagos-ai / FlagGems
  FlagGems is an operator library for large language models implemented in the Triton Language.
  ☆773Updated last week
• Tencent / KsanaLLM
  ☆514Updated 2 weeks ago
• Azure / MS-AMP
  Microsoft Automatic Mixed Precision Library
  ☆628Updated this week
• IST-DASLab / marlin
  FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.
  ☆958Updated last year
• fzyzcjy / torch_memory_saver
  Allow torch tensor memory to be released and resumed later
  ☆177Updated last week
• AmadeusChan / Awesome-LLM-System-Papers
  ☆610Updated 6 months ago
• ServerlessLLM / ServerlessLLM
  Serverless LLM Serving for Everyone.
  ☆618Updated this week
• stepfun-ai / StepMesh
  ☆324Updated 3 weeks ago
• mit-han-lab / omniserve
  [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…
  ☆786Updated 9 months ago