MegEngine / InferLLMLinks
a lightweight LLM model inference framework
☆738Updated last year
Alternatives and similar repositories for InferLLM
Users that are interested in InferLLM are comparing it to the libraries listed below
Sorting:
- C++ implementation of Qwen-LM☆609Updated 8 months ago
- llm deploy project based mnn. This project has merged into MNN.☆1,596Updated 7 months ago
- llm-export can export llm model to onnx.☆304Updated 7 months ago
- 支持中文场景的的小语言模型 llama2.c-zh☆149Updated last year
- RTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.☆840Updated last month
- ☆485Updated 3 weeks ago
- LLaMa/RWKV onnx models, quantization and testcase☆365Updated 2 years ago
- DashInfer is a native LLM inference engine aiming to deliver industry-leading performance atop various hardware architectures, including …☆263Updated 3 weeks ago
- Efficient AI Inference & Serving☆476Updated last year
- export llama to onnx☆132Updated 8 months ago
- ☆427Updated last week
- Accelerate inference without tears☆322Updated 5 months ago
- LLM Inference benchmark☆426Updated last year
- optimized BERT transformer inference on NVIDIA GPU. https://arxiv.org/abs/2210.03052☆475Updated last year
- ☆172Updated this week
- fastllm是后端无依赖的高性能大模型推理库。同时支持张量并行推理稠密模型和混合模式推理MOE模型,任意10G以上显卡即可推理满血DeepSeek。双路9004/9005服务器+单显卡部署DeepSeek满血满精度原版模型,单并发20tps;INT4量化模型单并发30tp…☆3,877Updated this week
- 中文Mixtral混合专家大模型(Chinese Mixtral MoE LLMs)☆608Updated last year
- Yuan 2.0 Large Language Model☆689Updated last year
- A powerful toolkit for compressing large models including LLM, VLM, and video generation models.☆550Updated last week
- torch_musa is an open source repository based on PyTorch, which can make full use of the super computing power of MooreThreads graphics c…☆434Updated 2 weeks ago
- ☆128Updated 8 months ago
- Ascend PyTorch adapter (torch_npu). Mirror of https://gitee.com/ascend/pytorch☆413Updated this week
- Low-bit LLM inference on CPU/NPU with lookup table☆845Updated 2 months ago
- Play LLaMA2 (official / 中文版 / INT4 / llama2.cpp) Together! ONLY 3 STEPS! ( non GPU / 5GB vRAM / 8~14GB vRAM)☆542Updated 2 years ago
- ☆140Updated last year
- A high-throughput and memory-efficient inference and serving engine for LLMs☆56Updated 10 months ago
- ☆622Updated last year
- XVERSE-13B: A multilingual large language model developed by XVERSE Technology Inc.☆644Updated last year
- The official repo of Aquila2 series proposed by BAAI, including pretrained & chat large language models.☆444Updated 10 months ago
- C++ implementation of ChatGLM-6B & ChatGLM2-6B & ChatGLM3 & GLM4(V)☆2,978Updated last year