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.
☆267Updated 3 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:
- ☆511Updated 2 months ago
- ☆129Updated 10 months ago
- Inferflow is an efficient and highly configurable inference engine for large language models (LLMs).☆249Updated last year
- FlagScale is a large model toolkit based on open-sourced projects.☆404Updated this week
- RTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.☆920Updated this week
- ☆431Updated last month
- LLM Inference benchmark☆428Updated last year
- Accelerate inference without tears☆365Updated 3 weeks ago
- Efficient AI Inference & Serving☆477Updated last year
- ☆64Updated last week
- ☆139Updated last year
- Compare different hardware platforms via the Roofline Model for LLM inference tasks.☆119Updated last year
- Model compression toolkit engineered for enhanced usability, comprehensiveness, and efficiency.☆197Updated this week
- optimized BERT transformer inference on NVIDIA GPU. https://arxiv.org/abs/2210.03052☆479Updated last year
- A high-performance inference system for large language models, designed for production environments.☆482Updated this week
- Transformer related optimization, including BERT, GPT☆39Updated 2 years ago
- Transformer related optimization, including BERT, GPT☆17Updated 2 years ago
- ☆79Updated last year
- ☆149Updated 8 months ago
- ☆205Updated 6 months ago
- Mixture-of-Experts (MoE) Language Model☆191Updated last year
- Transformer related optimization, including BERT, GPT☆59Updated 2 years ago
- export llama to onnx☆136Updated 10 months ago
- CPM.cu is a lightweight, high-performance CUDA implementation for LLMs, optimized for end-device inference and featuring cutting-edge tec…☆201Updated last month
- ☆176Updated this week
- InternEvo is an open-sourced lightweight training framework aims to support model pre-training without the need for extensive dependencie…☆411Updated 2 months ago
- Train speculative decoding models effortlessly and port them smoothly to SGLang serving.☆460Updated this week
- A flexible and efficient training framework for large-scale alignment tasks☆437Updated 2 weeks ago
- Ascend PyTorch adapter (torch_npu). Mirror of https://gitee.com/ascend/pytorch☆450Updated this week
- ☆72Updated last year