FlagOpen / FlagPerf
FlagPerf is an open-source software platform for benchmarking AI chips.
☆328Updated 2 months ago
Alternatives and similar repositories for FlagPerf:
Users that are interested in FlagPerf are comparing it to the libraries listed below
- GLake: optimizing GPU memory management and IO transmission.☆456Updated 3 weeks ago
- ☆326Updated 3 months ago
- FlagScale is a large model toolkit based on open-sourced projects.☆265Updated this week
- AI Accelerator Benchmark focuses on evaluating AI Accelerators from a practical production perspective, including the ease of use and ver…☆234Updated 3 weeks ago
- FlagGems is an operator library for large language models implemented in Triton Language.☆488Updated this week
- ☆127Updated 3 months ago
- Easy Parallel Library (EPL) is a general and efficient deep learning framework for distributed model training.☆267Updated 2 years ago
- Disaggregated serving system for Large Language Models (LLMs).☆559Updated 2 weeks ago
- ☆68Updated 4 months ago
- ☆139Updated 11 months ago
- RTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.☆702Updated 2 months ago
- ☆66Updated 5 months ago
- ☆148Updated 3 months ago
- ☆49Updated this week
- TePDist (TEnsor Program DISTributed) is an HLO-level automatic distributed system for DL models.☆94Updated last year
- Efficient and easy multi-instance LLM serving☆374Updated this week
- optimized BERT transformer inference on NVIDIA GPU. https://arxiv.org/abs/2210.03052☆472Updated last year
- A model compilation solution for various hardware☆424Updated this week
- ☆58Updated 4 months ago
- A collection of memory efficient attention operators implemented in the Triton language.☆262Updated 10 months ago
- A highly optimized LLM inference acceleration engine for Llama and its variants.☆885Updated this week
- ☆474Updated last week
- DeepSeek-V3/R1 inference performance simulator☆111Updated 3 weeks ago
- MIXQ: Taming Dynamic Outliers in Mixed-Precision Quantization by Online Prediction☆87Updated 5 months ago
- A baseline repository of Auto-Parallelism in Training Neural Networks☆144Updated 2 years ago
- PyTorch distributed training acceleration framework☆48Updated 2 months ago
- An industrial extension library of pytorch to accelerate large scale model training☆32Updated 2 months ago
- A low-latency & high-throughput serving engine for LLMs☆341Updated this week
- An acceleration library that supports arbitrary bit-width combinatorial quantization operations☆221Updated 6 months ago
- DashInfer is a native LLM inference engine aiming to deliver industry-leading performance atop various hardware architectures, including …☆242Updated this week