Yet Another Language Model: LLM inference in C++/CUDA, no libraries except for I/O
☆596Sep 13, 2025Updated 11 months ago
Alternatives and similar repositories for yalm
Users that are interested in yalm are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- CUDA/Metal accelerated language model inference☆646May 29, 2025Updated last year
- CPU inference for the DeepSeek family of large language models in C++☆322Oct 2, 2025Updated 11 months ago
- Modern CUDA Learn Notes with PyTorch for Beginners, 200+ CUDA Kernels, Tensor Cores, HGEMM, FA-2 MMA.☆11,900Updated this week
- Examples of CUDA implementations by Cutlass CuTe☆282Jul 1, 2025Updated last year
- 使用 CUDA C++ 实现的 llama 模型推理框架☆64Nov 8, 2024Updated last year
- 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.
- Nano vLLM☆15,333Apr 26, 2026Updated 4 months ago
- A compact implementation of SGLang, designed to demystify the complexities of modern LLM serving systems.☆4,990May 17, 2026Updated 3 months ago
- Static suckless single batch CUDA-only qwen3-0.6B mini inference engine☆559Sep 8, 2025Updated last year
- flash attention tutorial written in python, triton, cuda, cutlass☆534Jan 20, 2026Updated 7 months ago
- FlashInfer: Kernel Library for LLM Serving☆6,343Updated this week
- ☆192May 11, 2026Updated 3 months ago
- Flash Attention in ~100 lines of CUDA (forward pass only)☆1,180Dec 30, 2024Updated last year
- Material for gpu-mode lectures☆6,560Jun 15, 2026Updated 2 months ago
- Fast low-bit matmul kernels in Triton☆483Aug 9, 2026Updated 3 weeks ago
- AI Agents on DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- Fast CUDA matrix multiplication from scratch☆1,299Sep 2, 2025Updated last year
- ⚡️Write HGEMM from scratch using Tensor Cores with WMMA, MMA and CuTe API, Achieve Peak⚡️ Performance.☆158May 10, 2025Updated last year
- Kernels, of the mega variety :)☆820May 26, 2026Updated 3 months ago
- 📚A curated list of Awesome LLM/VLM Inference Papers with Codes: Flash-Attention, Paged-Attention, WINT8/4, Parallelism, etc.🎉☆5,489Aug 14, 2026Updated 3 weeks ago
- Sparse & quantized LLM training/inference/CPT/SFT/DPO☆28Aug 26, 2026Updated last week
- CPM.cu is a lightweight, high-performance CUDA implementation for LLMs, optimized for end-device inference and featuring cutting-edge tec…☆241Jan 14, 2026Updated 7 months ago
- GEMV implementation with CUTLASS☆21Aug 21, 2025Updated last year
- High Performance LLM Inference Operator Library☆1,146Updated this week
- Tile primitives for speedy kernels☆3,667Aug 28, 2026Updated last week
- 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.
- Implement Flash Attention using Cute.☆111Dec 17, 2024Updated last year
- My learning notes for ML SYS.☆7,269Aug 19, 2026Updated 2 weeks ago
- ☆13Apr 10, 2026Updated 4 months ago
- Enlightener, the cutting-edge Retrieval-Augmented Generation (RAG) system that revolutionizes query responses. By combining the power of …☆13Jul 28, 2025Updated last year
- learn LLM inference system on Apple Silicon for systems engineers: build a tiny vLLM + Qwen☆4,549Updated this week
- Decoding Attention is specially optimized for MHA, MQA, GQA and MLA using CUDA core for the decoding stage of LLM inference.☆48Jun 11, 2025Updated last year
- From Minimal GEMM to Everything☆241Jul 9, 2026Updated last month
- Minimalistic 4D-parallelism distributed training framework for education purpose☆2,296Aug 26, 2025Updated last year
- Puzzles for learning Triton☆2,588Apr 1, 2026Updated 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.
- how to optimize some algorithm in cuda.☆3,246Updated this week
- Efficient Triton Kernels for LLM Training☆6,602Updated this week
- Mirage Persistent Kernel: Compiling LLMs into a MegaKernel☆2,482Updated this week
- Puzzles for learning Triton, play it with minimal environment configuration!☆745Mar 17, 2026Updated 5 months ago
- Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.☆6,516Updated this week
- A Quirky Assortment of CuTe Kernels☆1,137Updated this week
- A throughput-oriented high-performance serving framework for LLMs☆975Mar 29, 2026Updated 5 months ago