modelscope / dash-inferLinks
DashInfer is a native LLM inference engine aiming to deliver industry-leading performance atop various hardware architectures, including CUDA, x86 and ARMv9.
☆262Updated 2 months ago
Alternatives and similar repositories for dash-infer
Users that are interested in dash-infer are comparing it to the libraries listed below
Sorting:
- ☆470Updated last week
- ☆128Updated 7 months ago
- RTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.☆817Updated last month
- FlagScale is a large model toolkit based on open-sourced projects.☆329Updated last week
- Inferflow is an efficient and highly configurable inference engine for large language models (LLMs).☆244Updated last year
- ☆52Updated 2 weeks ago
- ☆429Updated last week
- LLM Inference benchmark☆424Updated last year
- InternEvo is an open-sourced lightweight training framework aims to support model pre-training without the need for extensive dependencie…☆398Updated last week
- Accelerate inference without tears☆321Updated 4 months ago
- Compare different hardware platforms via the Roofline Model for LLM inference tasks.☆109Updated last year
- ☆139Updated last year
- Efficient AI Inference & Serving☆472Updated last year
- ☆195Updated 2 months ago
- optimized BERT transformer inference on NVIDIA GPU. https://arxiv.org/abs/2210.03052☆474Updated last year
- A high-performance inference system for large language models, designed for production environments.☆457Updated last week
- ☆145Updated 4 months ago
- A flexible and efficient training framework for large-scale alignment tasks☆395Updated this week
- [EMNLP 2024 Industry Track] This is the official PyTorch implementation of "LLMC: Benchmarking Large Language Model Quantization with a V…☆522Updated this week
- ☆170Updated this week
- Ascend PyTorch adapter (torch_npu). Mirror of https://gitee.com/ascend/pytorch☆395Updated last week
- Transformer related optimization, including BERT, GPT☆39Updated 2 years ago
- export llama to onnx☆130Updated 7 months ago
- A quantization algorithm for LLM☆141Updated last year
- CPM.cu is a lightweight, high-performance CUDA implementation for LLMs, optimized for end-device inference and featuring cutting-edge tec…☆163Updated 3 weeks ago
- ☆79Updated last year
- Transformer related optimization, including BERT, GPT☆59Updated last year
- UltraScale Playbook 中文版☆47Updated 4 months ago
- Materials for learning SGLang☆515Updated 2 weeks ago
- Mixture-of-Experts (MoE) Language Model☆189Updated 10 months ago