FlagOpen / FlagScale
FlagScale is a large model toolkit based on open-sourced projects.
☆263Updated last week
Alternatives and similar repositories for FlagScale:
Users that are interested in FlagScale are comparing it to the libraries listed below
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference☆473Updated this week
- A collection of memory efficient attention operators implemented in the Triton language.☆262Updated 10 months ago
- A flexible and efficient training framework for large-scale alignment tasks☆342Updated 2 months ago
- InternEvo is an open-sourced lightweight training framework aims to support model pre-training without the need for extensive dependencie…☆374Updated this week
- Disaggregated serving system for Large Language Models (LLMs).☆550Updated last week
- ☆127Updated 3 months ago
- ☆326Updated 2 months ago
- RTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.☆689Updated 2 months ago
- ☆131Updated last month
- FlagGems is an operator library for large language models implemented in Triton Language.☆488Updated this week
- Zero Bubble Pipeline Parallelism☆382Updated last week
- DashInfer is a native LLM inference engine aiming to deliver industry-leading performance atop various hardware architectures, including …☆244Updated last week
- Best practice for training LLaMA models in Megatron-LM☆649Updated last year
- Analyze the inference of Large Language Models (LLMs). Analyze aspects like computation, storage, transmission, and hardware roofline mod…☆438Updated 7 months ago
- Dynamic Memory Management for Serving LLMs without PagedAttention☆347Updated 3 weeks ago
- ☆139Updated 11 months ago
- PyTorch bindings for CUTLASS grouped GEMM.☆118Updated 3 months ago
- GLake: optimizing GPU memory management and IO transmission.☆456Updated 3 weeks ago
- Materials for learning SGLang☆379Updated 3 weeks ago
- [USENIX ATC '24] Accelerating the Training of Large Language Models using Efficient Activation Rematerialization and Optimal Hybrid Paral…☆51Updated 8 months ago
- A low-latency & high-throughput serving engine for LLMs☆341Updated 2 months ago
- ☆47Updated last week
- Community maintained hardware plugin for vLLM on Ascend☆459Updated this week
- [EMNLP 2024 Industry Track] This is the official PyTorch implementation of "LLMC: Benchmarking Large Language Model Quantization with a V…☆452Updated last week
- Ascend PyTorch adapter (torch_npu). Mirror of https://gitee.com/ascend/pytorch☆328Updated this week
- Efficient and easy multi-instance LLM serving☆374Updated this week
- [NeurIPS'23] H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models.☆438Updated 8 months ago
- AI Accelerator Benchmark focuses on evaluating AI Accelerators from a practical production perspective, including the ease of use and ver…☆234Updated 3 weeks ago
- Inferflow is an efficient and highly configurable inference engine for large language models (LLMs).☆242Updated last year
- The official repo of Pai-Megatron-Patch for LLM & VLM large scale training developed by Alibaba Cloud.☆998Updated this week