IMMA-based **FP8-as-storage** GEMM experiments for Ampere (sm_86 / RTX 3090 Ti).
☆28Jan 30, 2026Updated 8 months ago
Alternatives and similar repositories for cuda-fp8-ampere
Users that are interested in cuda-fp8-ampere are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆14Nov 3, 2025Updated 11 months ago
- High-performance GPU kernels for LLM inference in OpenAI Triton. Fused RMSNorm, SwiGLU, INT8 GEMM with benchmarks and roofline analysis.☆45Jul 22, 2026Updated 2 months ago
- Scripts and tools for optimizing quantizations in llama.cpp with GGUF imatrices.☆19Jan 10, 2025Updated last year
- Row-wise block scaling for fp8 quantization matrix multiplication. Solution to GPU mode AMD challenge.☆19Feb 9, 2026Updated 8 months ago
- 本仓库在OpenVINO推理框架下部署Nanodet检测算法，并重写预处理和后处理部分，具有超高性能！让你在Intel CPU平台上的检测速度起飞！ 并基于NNCF和PPQ工具将模型量化(PTQ)至int8精度，推理速度更快！☆16Jun 14, 2023Updated 3 years ago
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- ☆19Jan 4, 2024Updated 2 years ago
- An OpenAI API compatible FastAPI server that sits on top of the Anemll repo. Tested with Open WebUI.☆21Jan 21, 2026Updated 8 months ago
- Repo for YouTube tutorial on how to self-host a MinIo instance and connect a Next.js 15 app to MinIo and upload files☆20Jan 15, 2025Updated last year
- A ComfyUI custom node implementation of TwinFlow: Realizing One-step Generation on Large Models with Self-adversarial Flows.☆45Mar 6, 2026Updated 7 months ago
- Matrix multiplication on GPUs for matrices stored on a CPU. Similar to cublasXt, but ported to both NVIDIA and AMD GPUs.☆33Apr 2, 2025Updated last year
- LociTerm is a Progressive Web App that provides MUD Telnet connectivity to any platform with a JavaScript enabled Web Browser, through a …☆19Feb 3, 2026Updated 8 months ago
- ComfyUI-AudioLoopHelper☆17Jul 5, 2026Updated 3 months ago
- 对 tensorRT_Pro 开源项目理解☆22Feb 23, 2023Updated 3 years ago
- Linear-scaling compute & memory spline manifold for regression and interpolation☆19Feb 17, 2026Updated 7 months ago
- End-to-end encrypted cloud storage - Proton Drive • AdSpecial offer: 40% Off Yearly / 80% Off First Month. Protect your most important files, photos, and documents from prying eyes.
- ☆34Jul 23, 2024Updated 2 years ago
- This is a repository to practice multi-thread programming in C++☆33Feb 21, 2024Updated 2 years ago
- C++ / CUDA implementation of StreamDiffusion☆39Updated this week
- ComfyUI custom nodes for LTXV2, FLUX, other models.☆16Oct 2, 2026Updated last week
- ☆18Oct 12, 2025Updated 11 months ago
- 手摸手 美团 YOLOv6模型训练和TensorRT端到端部署方案教程☆34Jun 30, 2022Updated 4 years ago
- CUDA 8-bit Tensor Core Matrix Multiplication based on m16n16k16 WMMA API☆38Sep 15, 2023Updated 3 years ago
- Generate talking-head videos with custom character faces and voices directly within ComfyUI.☆21Mar 20, 2026Updated 6 months ago
- Matrix Multiplication on GPU using Shared Memory considering Coalescing and Bank Conflicts☆26Aug 29, 2022Updated 4 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.
- Internal Coherence Maximization (ICM): A Label-Free, Unsupervised Training Framework for LLMs☆27Sep 5, 2025Updated last year
- This project is intended to build and deploy an SNPE model on Qualcomm Devices, which are having unsupported layers which are not part of…☆10Oct 4, 2021Updated 5 years ago
- MobileSAM のエンコーダー/デコーダーをONNXに変換し、推論するサンプル☆12Apr 11, 2024Updated 2 years ago
- YOLOv12 TensorRT 端到端模型加速推理和INT8量化实现☆14Mar 5, 2025Updated last year
- Converts CLIP models to ONNX☆11Jan 17, 2023Updated 3 years ago
- Multi-GPU device selection for LTXV2 video generation in ComfyUI☆34Jan 10, 2026Updated 9 months ago
- GEMM☆10Aug 26, 2023Updated 3 years ago
- Penn CIS 5650 (GPU Programming and Architecture) Final Project☆46Dec 11, 2023Updated 2 years ago
- Evolutionary strategies finetuning library for LLMs☆25Sep 12, 2026Updated 3 weeks ago
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- 使用ONNXRuntime部署一种用于边缘检测的轻量级密集卷积神经网络LDC，包含C++和Python两个版本的程序☆12Apr 24, 2023Updated 3 years ago
- LDC: Lightweight Dense CNN for Edge DetectionのPythonでのONNX推論サンプル☆15May 6, 2023Updated 3 years ago
- ☆20Updated this week
- Simple GUI editor for Ideogram V4's structured JSON prompts☆27Jun 10, 2026Updated 4 months ago
- A handy plugin for copying requests/responses directly from Burp, some extra magic included.☆13Oct 15, 2021Updated 4 years ago
- vscode support for chez shame☆10Dec 3, 2019Updated 6 years ago
- DETR tensor去除推理过程无用辅助头+fp16部署再次加速+解决转tensorrt 输出全为0问题的新方法。☆12Jan 9, 2024Updated 2 years ago