IMMA-based **FP8-as-storage** GEMM experiments for Ampere (sm_86 / RTX 3090 Ti).
☆24Jan 30, 2026Updated 5 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 8 months ago
- High-performance GPU kernels for LLM inference in OpenAI Triton. Fused RMSNorm, SwiGLU, INT8 GEMM with benchmarks and roofline analysis.☆31Apr 5, 2026Updated 3 months ago
- Row-wise block scaling for fp8 quantization matrix multiplication. Solution to GPU mode AMD challenge.☆19Feb 9, 2026Updated 5 months ago
- Fast INT4 model inference custom node for ComfyUI leveraging Tensor Cores.☆30Jul 10, 2026Updated last week
- 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
- 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.
- ☆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 5 months ago
- A ComfyUI custom node implementation of TwinFlow: Realizing One-step Generation on Large Models with Self-adversarial Flows.☆44Mar 6, 2026Updated 4 months ago
- ☆21Mar 5, 2024Updated 2 years 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
- 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 5 months ago
- ☆34Jul 23, 2024Updated last year
- My submission for the GPUMODE/AMD fp8 mm challenge☆29Jun 4, 2025Updated last year
- GPUs on demand by Runpod - Special Offer Available • AdRun AI, ML, and HPC workloads on powerful cloud GPUs—without limits or wasted spend. Deploy GPUs in under a minute and pay by the second.
- ComfyUI custom nodes for LTXV2, FLUX, other models.☆15Jul 5, 2026Updated 2 weeks ago
- ☆15Oct 12, 2025Updated 9 months ago
- ☆30Nov 16, 2024Updated last year
- 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☆37Sep 15, 2023Updated 2 years ago
- An MCP-enabled Qwen3 0.6B demo with adjustable thinking budget, all in your browser!☆28Jun 2, 2025Updated last year
- Matrix Multiplication on GPU using Shared Memory considering Coalescing and Bank Conflicts☆26Aug 29, 2022Updated 3 years ago
- Internal Coherence Maximization (ICM): A Label-Free, Unsupervised Training Framework for LLMs☆27Sep 5, 2025Updated 10 months ago
- 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 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.
- 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
- Converts CLIP models to ONNX☆11Jan 17, 2023Updated 3 years ago
- Generate talking-head videos with custom character faces and voices directly within ComfyUI.☆20Mar 20, 2026Updated 4 months ago
- GEMM☆10Aug 26, 2023Updated 2 years ago
- Penn CIS 5650 (GPU Programming and Architecture) Final Project☆44Dec 11, 2023Updated 2 years ago
- 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☆11Apr 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
- SNDR Core Engine (Genesis) — vLLM runtime patch-overlay for Qwen3.6 + Gemma4 on consumer NVIDIA (Ampere sm_86, 2× A5000/3090). Qwen3.6-35…☆125Updated this week
- A Chinese-focused PyTorch framework for exploring Attention Residuals in Qwen3-style causal LMs, with baseline, Block AttnRes, Full AttnR…☆19May 3, 2026Updated 2 months ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- ☆18Updated this week
- This project provides a relay that can accept metrics in various formats (initially Graphite Line protocol) and send them through various…☆22Mar 20, 2018Updated 8 years ago
- ☆10Jul 28, 2021Updated 4 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
- Simple GUI editor for Ideogram V4's structured JSON prompts☆25Jun 10, 2026Updated last month
- ☆10Jul 18, 2024Updated 2 years ago
- ☆11May 16, 2026Updated 2 months ago