Run generative AI models in sophgo BM1684X/BM1688
☆279Apr 1, 2026Updated 2 weeks ago
Alternatives and similar repositories for LLM-TPU
Users that are interested in LLM-TPU are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆484Apr 1, 2026Updated 2 weeks ago
- Machine learning compiler based on MLIR for Sophgo TPU.☆898Apr 1, 2026Updated 2 weeks ago
- 适用于sophon bm1684x，基于 Langchain 与 ChatGLM 等语言模型的本地知识库问答☆14Jun 5, 2024Updated last year
- ChatTTS is a generative speech model for daily dialogue.☆14Oct 21, 2024Updated last year
- run ChatGLM2-6B in BM1684X☆49Mar 1, 2024Updated 2 years ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- ☆138Mar 12, 2026Updated last month
- Sophgo AI chips driver and runtime library.☆24Apr 3, 2026Updated last week
- Text2speech & tone color conversion demo running on SG2300x 结合openvoice和emotivoice的TTS+即时克隆☆22Oct 30, 2024Updated last year
- run chatglm3-6b in BM1684X☆39Mar 1, 2024Updated 2 years ago
- A whisper repo for TPU☆11Jun 4, 2024Updated last year
- Stable Diffusion+LCM在SG2300X上，纵享丝滑一秒出图☆17Nov 29, 2024Updated last year
- llm deploy project based onnx.☆50Oct 9, 2024Updated last year
- cvitek ai compiler base on MLIR☆23Mar 14, 2022Updated 4 years ago
- llm-export can export llm model to onnx.☆347Oct 24, 2025Updated 5 months ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- JAX bindings for the flash-attention3 kernels☆22Jan 2, 2026Updated 3 months ago
- ☆1,368Mar 12, 2026Updated last month
- Explore LLM model deployment based on AXera's AI chips☆148Apr 1, 2026Updated 2 weeks ago
- sophon-tools（xun.li，mingxuan.che)☆21Updated this week
- Development repository for the Triton-Linalg conversion☆218Feb 7, 2025Updated last year
- 万物检测（零样本检测+识别） demo for SG2300X 【Recognize Anything + GroundingDINO】☆24May 9, 2024Updated last year
- ☆20Dec 3, 2025Updated 4 months ago
- Deepseek-r1复现科普与资源汇总☆22Mar 5, 2025Updated last year
- Open source RTL implementation of Tensor Core, Sparse Tensor Core, BitWave and SparSynergy in the article: "SparSynergy: Unlocking Flexib…☆23Mar 29, 2025Updated last year
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- flow mirror models from JZX AI Labs☆43Sep 30, 2024Updated last year
- ☆30Jun 2, 2022Updated 3 years ago
- RISC-V vector and tensor compute extensions for Vortex GPGPU acceleration for ML workloads. Optimized for transformer models, CNNs, and g…☆23Apr 25, 2025Updated 11 months ago
- ☆2,855Jul 29, 2025Updated 8 months ago
- ☆2,391Apr 9, 2025Updated last year
- 基于SG2300X的视频检索【使用自然语言搜索视频内容，定位到符合描述的具体时间段】☆13Feb 29, 2024Updated 2 years ago
- [HPCA'21] SpAtten: Efficient Sparse Attention Architecture with Cascade Token and Head Pruning☆128Aug 27, 2024Updated last year
- a clone of POCL that includes RISC-V newlib devices support and Vortex☆49Jan 14, 2026Updated 3 months ago
- Examples for SophonSDK☆108Aug 11, 2022Updated 3 years ago
- Serverless GPU API endpoints on Runpod - Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- 基于rknn的官方Android项目rknn_yolov5_android_apk_demo进行修改，部署人脸检测模型retinaface和106人脸关键点检测模型，支持实时人脸检测。支持rk356x和rk3588设备npu推理。☆25Mar 14, 2024Updated 2 years ago
- Quantize yolov5 using pytorch_quantization.🚀🚀🚀☆14Oct 24, 2023Updated 2 years ago
- Model Quantization Benchmark☆18Mar 23, 2026Updated 3 weeks ago
- Artifact evaluation of PLDI'24 paper "Allo: A Programming Model for Composable Accelerator Design"☆33Apr 11, 2024Updated 2 years ago
- An MLIR-based compiler framework bridges DSLs (domain-specific languages) to DSAs (domain-specific architectures).☆706Updated this week
- [EMNLP 2024 & AAAI 2026] A powerful toolkit for compressing large models including LLMs, VLMs, and video generative models.☆698Apr 1, 2026Updated 2 weeks ago
- NVIDIA TensorRT Hackathon 2023复赛选题：通义千问Qwen-7B用TensorRT-LLM模型搭建及优化☆43Oct 20, 2023Updated 2 years ago