Alternatives and similar repositories for veScale:

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

• bytedance / flux
  A fast communication-overlapping library for tensor/expert parallelism on GPUs.
  ☆864Updated 2 weeks ago
• efeslab / Nanoflow
  A throughput-oriented high-performance serving framework for LLMs
  ☆794Updated 6 months ago
• LLMServe / DistServe
  Disaggregated serving system for Large Language Models (LLMs).
  ☆550Updated last week
• sail-sg / zero-bubble-pipeline-parallelism
  Zero Bubble Pipeline Parallelism
  ☆382Updated last week
• zhuzilin / ring-flash-attention
  Ring attention implementation with flash attention
  ☆734Updated last week
• ByteDance-Seed / Triton-distributed
  Distributed Triton for Parallel Systems
  ☆415Updated last week
• AlibabaPAI / llumnix
  Efficient and easy multi-instance LLM serving
  ☆374Updated this week
• feifeibear / long-context-attention
  USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference
  ☆473Updated this week
• flashinfer-ai / flashinfer
  FlashInfer: Kernel Library for LLM Serving
  ☆2,659Updated last week
• microsoft / vattention
  Dynamic Memory Management for Serving LLMs without PagedAttention
  ☆347Updated 3 weeks ago
• antgroup / glake
  GLake: optimizing GPU memory management and IO transmission.
  ☆456Updated 3 weeks ago
• FlagOpen / FlagScale
  FlagScale is a large model toolkit based on open-sourced projects.
  ☆263Updated last week
• sgl-project / sgl-learning-materials
  Materials for learning SGLang
  ☆379Updated 3 weeks ago
• tile-ai / tilelang
  Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels
  ☆971Updated this week
• 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…
  ☆639Updated last month
• alibaba / rtp-llm
  RTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.
  ☆689Updated 2 months ago
• FlagOpen / FlagGems
  FlagGems is an operator library for large language models implemented in Triton Language.
  ☆488Updated this week
• hahnyuan / LLM-Viewer
  Analyze the inference of Large Language Models (LLMs). Analyze aspects like computation, storage, transmission, and hardware roofline mod…
  ☆438Updated 7 months ago
• FlagOpen / FlagAttention
  A collection of memory efficient attention operators implemented in the Triton language.
  ☆262Updated 10 months ago
• Azure / MS-AMP
  Microsoft Automatic Mixed Precision Library
  ☆591Updated 6 months ago
• microsoft / sarathi-serve
  A low-latency & high-throughput serving engine for LLMs
  ☆341Updated 2 months ago
• IST-DASLab / marlin
  FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.
  ☆797Updated 7 months ago
• microsoft / vidur
  A large-scale simulation framework for LLM inference
  ☆361Updated 4 months ago
• cli99 / llm-analysis
  Latency and Memory Analysis of Transformer Models for Training and Inference
  ☆403Updated last month
• NVIDIA / nccl-tests
  NCCL Tests
  ☆1,065Updated last month
• alibaba / Megatron-LLaMA
  Best practice for training LLaMA models in Megatron-LM
  ☆649Updated last year
• mirage-project / mirage
  Mirage: Automatically Generating Fast GPU Kernels without Programming in Triton/CUDA
  ☆798Updated this week
• pcg-mlp / KsanaLLM
  ☆326Updated 2 months ago
• SafeAILab / EAGLE
  Official Implementation of EAGLE-1 (ICML'24), EAGLE-2 (EMNLP'24), and EAGLE-3.
  ☆1,169Updated this week
• LMCache / LMCache
  Redis for LLMs
  ☆808Updated this week