Ascend / AscendSpeedLinks
☆79Updated last year
Alternatives and similar repositories for AscendSpeed
Users that are interested in AscendSpeed are comparing it to the libraries listed below
Sorting:
- Transformer related optimization, including BERT, GPT☆59Updated last year
- A MoE impl for PyTorch, [ATC'23] SmartMoE☆66Updated 2 years ago
- ☆128Updated 7 months ago
- LiBai(李白): A Toolbox for Large-Scale Distributed Parallel Training☆409Updated last week
- ☆220Updated last year
- Models and examples built with OneFlow☆98Updated 9 months ago
- Compare different hardware platforms via the Roofline Model for LLM inference tasks.☆110Updated last year
- Transformer related optimization, including BERT, GPT☆17Updated 2 years ago
- ☆16Updated last year
- Inferflow is an efficient and highly configurable inference engine for large language models (LLMs).☆244Updated last year
- ☆52Updated this week
- optimized BERT transformer inference on NVIDIA GPU. https://arxiv.org/abs/2210.03052☆474Updated last year
- Transformer related optimization, including BERT, GPT☆39Updated 2 years ago
- An easy-to-use package for implementing SmoothQuant for LLMs☆102Updated 3 months ago
- FlagScale is a large model toolkit based on open-sourced projects.☆333Updated this week
- Train llm (bloom, llama, baichuan2-7b, chatglm3-6b) with deepspeed pipeline mode. Faster than zero/zero++/fsdp.☆97Updated last year
- ☆145Updated 4 months ago
- DashInfer is a native LLM inference engine aiming to deliver industry-leading performance atop various hardware architectures, including …☆262Updated 2 months ago
- A collection of memory efficient attention operators implemented in the Triton language.☆273Updated last year
- ☆92Updated 4 months ago
- ☆139Updated last year
- Efficient, Flexible, and Highly Fault-Tolerant Model Service Management Based on SGLang☆55Updated 8 months ago
- PyTorch bindings for CUTLASS grouped GEMM.☆134Updated 2 weeks ago
- Model Compression for Big Models☆164Updated 2 years ago
- InternEvo is an open-sourced lightweight training framework aims to support model pre-training without the need for extensive dependencie…☆398Updated last week
- A quantization algorithm for LLM☆141Updated last year
- ☆120Updated last year
- Sequence-level 1F1B schedule for LLMs.☆17Updated last year
- Fast and memory-efficient exact attention☆82Updated this week
- Simple Dynamic Batching Inference☆145Updated 3 years ago