Alternatives and similar repositories for FlagScale:

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

• LLMServe / DistServe
  Disaggregated serving system for Large Language Models (LLMs).
  ☆580Updated last month
• feifeibear / long-context-attention
  USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference
  ☆490Updated 2 weeks ago
• madsys-dev / deepseekv2-profile
  ☆131Updated 2 months ago
• alibaba / rtp-llm
  RTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.
  ☆715Updated 3 months ago
• FlagOpen / FlagAttention
  A collection of memory efficient attention operators implemented in the Triton language.
  ☆266Updated 11 months ago
• alibaba / ChatLearn
  A flexible and efficient training framework for large-scale alignment tasks
  ☆345Updated 2 months ago
• InternLM / InternEvo
  InternEvo is an open-sourced lightweight training framework aims to support model pre-training without the need for extensive dependencie…
  ☆385Updated 2 weeks ago
• sgl-project / sgl-learning-materials
  Materials for learning SGLang
  ☆406Updated last week
• pcg-mlp / KsanaLLM
  ☆328Updated 3 months ago
• OpenPPL / ppl.llm.serving
  ☆127Updated 4 months ago
• modelscope / dash-infer
  DashInfer is a native LLM inference engine aiming to deliver industry-leading performance atop various hardware architectures, including …
  ☆245Updated 2 weeks ago
• hahnyuan / LLM-Viewer
  Analyze the inference of Large Language Models (LLMs). Analyze aspects like computation, storage, transmission, and hardware roofline mod…
  ☆450Updated 7 months ago
• sail-sg / zero-bubble-pipeline-parallelism
  Zero Bubble Pipeline Parallelism
  ☆387Updated this week
• FlagOpen / FlagGems
  FlagGems is an operator library for large language models implemented in Triton Language.
  ☆516Updated this week
• fanshiqing / grouped_gemm
  PyTorch bindings for CUTLASS grouped GEMM.
  ☆120Updated 4 months ago
• alibaba / Megatron-LLaMA
  Best practice for training LLaMA models in Megatron-LM
  ☆650Updated last year
• antgroup / glake
  GLake: optimizing GPU memory management and IO transmission.
  ☆457Updated last month
• alibaba / Pai-Megatron-Patch
  The official repo of Pai-Megatron-Patch for LLM & VLM large scale training developed by Alibaba Cloud.
  ☆1,050Updated last week
• DeepLink-org / dlinfer
  ☆48Updated last week
• microsoft / vattention
  Dynamic Memory Management for Serving LLMs without PagedAttention
  ☆364Updated 2 weeks ago
• ninehills / llm-inference-benchmark
  LLM Inference benchmark
  ☆416Updated 9 months ago
• ModelTC / llmc
  [EMNLP 2024 Industry Track] This is the official PyTorch implementation of "LLMC: Benchmarking Large Language Model Quantization with a V…
  ☆466Updated last week
• kwai / Megatron-Kwai
  [USENIX ATC '24] Accelerating the Training of Large Language Models using Efficient Activation Rematerialization and Optimal Hybrid Paral…
  ☆53Updated 9 months ago
• OpenPPL / ppl.nn.llm
  ☆139Updated last year
• vllm-project / vllm-ascend
  Community maintained hardware plugin for vLLM on Ascend
  ☆569Updated last week
• zhuzilin / ring-flash-attention
  Ring attention implementation with flash attention
  ☆759Updated last month
• AlibabaPAI / llumnix
  Efficient and easy multi-instance LLM serving
  ☆402Updated this week
• FlagOpen / FlagPerf
  FlagPerf is an open-source software platform for benchmarking AI chips.
  ☆331Updated 3 months ago
• bytedance / ByteTransformer
  optimized BERT transformer inference on NVIDIA GPU. https://arxiv.org/abs/2210.03052
  ☆473Updated last year
• microsoft / sarathi-serve
  A low-latency & high-throughput serving engine for LLMs
  ☆351Updated 2 weeks ago