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:
- ☆128Updated 6 months ago
- Transformer related optimization, including BERT, GPT☆59Updated last year
- An easy-to-use package for implementing SmoothQuant for LLMs☆102Updated 3 months ago
- Inferflow is an efficient and highly configurable inference engine for large language models (LLMs).☆243Updated last year
- A MoE impl for PyTorch, [ATC'23] SmartMoE☆64Updated 2 years ago
- ☆16Updated last year
- A collection of memory efficient attention operators implemented in the Triton language.☆272Updated last year
- ☆142Updated 4 months ago
- Compare different hardware platforms via the Roofline Model for LLM inference tasks.☆107Updated last year
- Models and examples built with OneFlow☆97Updated 8 months ago
- ☆220Updated last year
- FlagScale is a large model toolkit based on open-sourced projects.☆321Updated this week
- Transformer related optimization, including BERT, GPT☆17Updated last year
- ☆139Updated last year
- PyTorch bindings for CUTLASS grouped GEMM.☆130Updated 6 months ago
- ☆87Updated 3 months ago
- Train llm (bloom, llama, baichuan2-7b, chatglm3-6b) with deepspeed pipeline mode. Faster than zero/zero++/fsdp.☆97Updated last year
- optimized BERT transformer inference on NVIDIA GPU. https://arxiv.org/abs/2210.03052☆475Updated last year
- LiBai(李白): A Toolbox for Large-Scale Distributed Parallel Training☆408Updated 2 weeks ago
- ☆195Updated 2 months ago
- Efficient, Flexible, and Highly Fault-Tolerant Model Service Management Based on SGLang☆53Updated 8 months ago
- export llama to onnx☆128Updated 6 months ago
- Transformer related optimization, including BERT, GPT☆39Updated 2 years ago
- Performance of the C++ interface of flash attention and flash attention v2 in large language model (LLM) inference scenarios.☆39Updated 4 months ago
- Fast and memory-efficient exact attention☆80Updated this week
- A quantization algorithm for LLM☆141Updated last year
- DashInfer is a native LLM inference engine aiming to deliver industry-leading performance atop various hardware architectures, including …☆259Updated last month
- ATC23 AE☆45Updated 2 years ago
- Summary of system papers/frameworks/codes/tools on training or serving large model☆57Updated last year
- A flexible and efficient training framework for large-scale alignment tasks☆385Updated this week