Yet Another Language Model: LLM inference in C++/CUDA, no libraries except for I/O
☆595Sep 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++☆319Oct 2, 2025Updated 10 months ago
- Modern CUDA Learn Notes with PyTorch for Beginners, 200+ CUDA Kernels, Tensor Cores, HGEMM, FA-2 MMA.☆11,774Updated this week
- Examples of CUDA implementations by Cutlass CuTe☆281Jul 1, 2025Updated last year
- 使用 CUDA C++ 实现的 llama 模型推理框架☆64Nov 8, 2024Updated last year
- 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.
- Nano vLLM☆15,034Apr 26, 2026Updated 3 months ago
- A compact implementation of SGLang, designed to demystify the complexities of modern LLM serving systems.☆4,756May 17, 2026Updated 3 months ago
- Static suckless single batch CUDA-only qwen3-0.6B mini inference engine☆554Sep 8, 2025Updated 11 months ago
- flash attention tutorial written in python, triton, cuda, cutlass☆532Jan 20, 2026Updated 6 months ago
- FlashInfer: Kernel Library for LLM Serving☆6,179Updated this week
- ☆189May 11, 2026Updated 3 months ago
- Flash Attention in ~100 lines of CUDA (forward pass only)☆1,176Dec 30, 2024Updated last year
- Fast low-bit matmul kernels in Triton☆481Aug 9, 2026Updated last week
- Material for gpu-mode lectures☆6,451Jun 15, 2026Updated 2 months 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.
- Fast CUDA matrix multiplication from scratch☆1,283Sep 2, 2025Updated 11 months ago
- ⚡️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 :)☆804May 26, 2026Updated 2 months ago
- 📚A curated list of Awesome LLM/VLM Inference Papers with Codes: Flash-Attention, Paged-Attention, WINT8/4, Parallelism, etc.🎉☆5,454Updated this week
- Sparse & quantized LLM training/inference/CPT/SFT/DPO☆28Jul 28, 2026Updated 3 weeks ago
- CPM.cu is a lightweight, high-performance CUDA implementation for LLMs, optimized for end-device inference and featuring cutting-edge tec…☆242Jan 14, 2026Updated 7 months ago
- High Performance LLM Inference Operator Library☆1,118Aug 6, 2026Updated last week
- GEMV implementation with CUTLASS☆21Aug 21, 2025Updated 11 months ago
- Implement Flash Attention using Cute.☆111Dec 17, 2024Updated last year
- 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.
- My learning notes for ML SYS.☆6,879Updated this week
- Tile primitives for speedy kernels☆3,631Jul 13, 2026Updated last month
- Enlightener, the cutting-edge Retrieval-Augmented Generation (RAG) system that revolutionizes query responses. By combining the power of …☆13Jul 28, 2025Updated last year
- ☆13Apr 10, 2026Updated 4 months ago
- learn LLM inference system on Apple Silicon for systems engineers: build a tiny vLLM + Qwen☆4,497Updated 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☆234Jul 9, 2026Updated last month
- Minimalistic 4D-parallelism distributed training framework for education purpose☆2,282Aug 26, 2025Updated 11 months ago
- Puzzles for learning Triton☆2,563Apr 1, 2026Updated 4 months ago
- 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.
- how to optimize some algorithm in cuda.☆3,203Updated this week
- Efficient Triton Kernels for LLM Training☆6,569Updated this week
- Mirage Persistent Kernel: Compiling LLMs into a MegaKernel☆2,431Aug 4, 2026Updated last week
- Puzzles for learning Triton, play it with minimal environment configuration!☆746Mar 17, 2026Updated 5 months ago
- Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.☆6,300Updated this week
- A Quirky Assortment of CuTe Kernels☆1,116Updated this week
- A throughput-oriented high-performance serving framework for LLMs☆975Mar 29, 2026Updated 4 months ago