A high-throughput and memory-efficient inference and serving engine for LLMs
☆121Sep 18, 2026Updated this week
Alternatives and similar repositories for vllm-musa
Users that are interested in vllm-musa are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Get up and running with OpenAI gpt-oss, DeepSeek-R1, Gemma 3 and other models on MTGPU.☆37Oct 13, 2025Updated 11 months ago
- Fork from https://github.com/deepseek-ai/FlashMLA☆18Feb 26, 2025Updated last year
- An adapter layer that ensures torch_musa🔦 delivers a CUDA-compatible PyTorch experience.☆41Updated this 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…☆513Sep 9, 2026Updated last week
- Community maintained hardware plugin for vLLM on MetaX GPU☆174Updated this week
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels☆59Jun 5, 2026Updated 3 months ago
- ☆21Sep 2, 2026Updated 2 weeks ago
- DeepSeek-V3/R1 inference performance simulator☆195Mar 27, 2025Updated last year
- The quantization of CNN/LSTM☆11Mar 26, 2017Updated 9 years ago
- ☆15Apr 15, 2022Updated 4 years ago
- RISCV C and Triton AI-Benchmark☆26Jan 28, 2026Updated 7 months ago
- ☆156Mar 4, 2025Updated last year
- ☆856Updated this week
- Tile-Based Runtime for Ultra-Low-Latency LLM Inference☆1,780Aug 13, 2026Updated last month
- 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.
- ☆13Jan 7, 2025Updated last year
- Experimental TensorRT implementation of apple ml-depth-pro for faster inference☆22Oct 10, 2024Updated last year
- ☆120May 11, 2026Updated 4 months ago
- ☆20Sep 28, 2024Updated last year
- IPVS based kubernetes controller for large scale cluster autoscaling☆16Nov 29, 2019Updated 6 years ago
- Several optimization methods of half-precision general matrix vector multiplication (HGEMV) using CUDA core.☆76Sep 8, 2024Updated 2 years ago
- autoTVM神经网络推理代码优化搜索演示，基于tvm编译开源模型centerface，并使用autoTVM搜索最优推理代码， 最终部署编译为c++代码，演示平台是cuda，可以是其他平台，例如树莓派，安卓手机，苹果手机．Thi is a demonstration of …☆31May 6, 2021Updated 5 years ago
- High Performance LLM Inference Operator Library☆1,160Sep 7, 2026Updated last week
- ☆25Mar 15, 2023Updated 3 years 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.
- Compare different hardware platforms via the Roofline Model for LLM inference tasks.☆126Mar 13, 2024Updated 2 years ago
- Memory-efficient optimum einsum using opt_einsum planning and PyTorch kernels.☆16Apr 24, 2023Updated 3 years ago
- llm-inference is a platform for publishing and managing llm inference, providing a wide range of out-of-the-box features for model deploy…☆97May 17, 2024Updated 2 years ago
- 使用C++ tensorrt10 推理 ml-depth-pro 模型☆23Jan 8, 2025Updated last year
- Community maintained hardware plugin for vLLM on Ascend☆2,850Updated this week
- High performance RMSNorm Implement by using SM Core Storage(Registers and Shared Memory)☆31Jan 22, 2026Updated 7 months ago
- Development repository for the Triton-Linalg conversion☆225Feb 7, 2025Updated last year
- Fast and memory-efficient exact attention☆23Jun 26, 2026Updated 2 months ago
- High-performance LLM operator library built on TileLang.☆188Updated this week
- 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.
- FlashTile is a CUDA Tile IR compiler that is compatible with NVIDIA's tileiras, targeting SM70 through SM121 NVIDIA GPUs.☆60Feb 6, 2026Updated 7 months ago
- GPU implementation of Winograd convolution☆10Oct 23, 2017Updated 8 years ago
- A Winograd Minimal Filter Implementation in CUDA☆31Aug 25, 2021Updated 5 years ago
- YOLO-World-ONNX is a Python package for running inference on YOLO-WORLD Open-vocabulary-object detection model using ONNX models. It prov…☆18Feb 6, 2026Updated 7 months ago
- SGLang Kernel Wheel Index☆26Updated this week
- 打包工具parcel的中文文档和自己写的parcel使用demo☆15Mar 2, 2018Updated 8 years ago
- ncnn is a high-performance neural network inference framework optimized for the mobile platform☆14May 20, 2022Updated 4 years ago