FlagOpen / FlagPerfLinks
FlagPerf is an open-source software platform for benchmarking AI chips.
☆353Updated 2 months ago
Alternatives and similar repositories for FlagPerf
Users that are interested in FlagPerf are comparing it to the libraries listed below
Sorting:
- GLake: optimizing GPU memory management and IO transmission.☆480Updated 6 months ago
- FlagScale is a large model toolkit based on open-sourced projects.☆358Updated this week
- DLRover: An Automatic Distributed Deep Learning System☆1,559Updated last week
- ☆504Updated 3 weeks ago
- RTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.☆874Updated this week
- ☆70Updated 11 months ago
- A highly optimized LLM inference acceleration engine for Llama and its variants.☆900Updated 2 months ago
- ☆129Updated 9 months ago
- AI Accelerator Benchmark focuses on evaluating AI Accelerators from a practical production perspective, including the ease of use and ver…☆266Updated last month
- ☆75Updated 10 months ago
- ☆88Updated last week
- An acceleration library that supports arbitrary bit-width combinatorial quantization operations☆234Updated last year
- FlagGems is an operator library for large language models implemented in the Triton Language.☆690Updated this week
- Easy Parallel Library (EPL) is a general and efficient deep learning framework for distributed model training.☆268Updated 2 years ago
- DashInfer is a native LLM inference engine aiming to deliver industry-leading performance atop various hardware architectures, including …☆265Updated last month
- MIXQ: Taming Dynamic Outliers in Mixed-Precision Quantization by Online Prediction☆93Updated 11 months ago
- ☆429Updated 2 weeks ago
- ☆677Updated last week
- Disaggregated serving system for Large Language Models (LLMs).☆697Updated 5 months ago
- optimized BERT transformer inference on NVIDIA GPU. https://arxiv.org/abs/2210.03052☆478Updated last year
- Ascend PyTorch adapter (torch_npu). Mirror of https://gitee.com/ascend/pytorch☆434Updated 3 weeks ago
- Efficient and easy multi-instance LLM serving☆493Updated last month
- ☆140Updated last year
- DeepLearning Framework Performance Profiling Toolkit☆290Updated 3 years ago
- A PyTorch Native LLM Training Framework☆874Updated 3 weeks ago
- ☆150Updated 8 months ago
- TePDist (TEnsor Program DISTributed) is an HLO-level automatic distributed system for DL models.☆96Updated 2 years ago
- [USENIX ATC '24] Accelerating the Training of Large Language Models using Efficient Activation Rematerialization and Optimal Hybrid Paral…☆64Updated last year
- ☆58Updated 5 years ago
- 一种任务级GPU算力分时调度的高性能深度学习训练平台☆699Updated last year