Tiny C++ LLM inference implementation from scratch
☆132Jun 23, 2026Updated 4 months ago
Alternatives and similar repositories for TinyGPT
Users that are interested in TinyGPT are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- A lightweight deep learning training framework implemented from scratch in C++, featuring a PyTorch-style API.☆235Jun 23, 2026Updated 4 months ago
- Autonomous GPU kernel optimization system driven by AI agents.☆32Mar 29, 2026Updated 7 months ago
- VibeRL is a Reinforcement Learning framework built essentially through vibe coding with Kimi K2.☆18Nov 9, 2026Updated last week
- Efficient and unified implementations for TopK-based sparse attention☆41Jul 10, 2026Updated 4 months ago
- A high-throughput and memory-efficient inference and serving engine for LLMs☆17Jun 3, 2024Updated 2 years ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- Whisper in TensorRT-LLM☆16Sep 21, 2023Updated 3 years ago
- NCU-driven iterative optimization workflow for CUDA/CUTLASS/Triton/CuTe DSL kernels.☆25Apr 10, 2026Updated 7 months ago
- SGLang wheels for multiple platforms☆11Oct 13, 2025Updated last year
- ☆54May 19, 2025Updated last year
- A high-throughput and memory-efficient inference and serving engine for LLMs☆10Jul 22, 2023Updated 3 years ago
- Xmixers: A collection of SOTA efficient token/channel mixers☆29Sep 4, 2025Updated last year
- Tengine 管子是用来快速生产 demo 的辅助工具☆11Jul 15, 2021Updated 5 years ago
- CUDA SGEMM optimization note☆16Oct 31, 2023Updated 3 years ago
- ☆37Aug 7, 2025Updated last year
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- ☆11Dec 26, 2025Updated 10 months ago
- Breakable CUDA graph capture for PyTorch - capture compatible regions as CUDA graphs while running incompatible operations eagerly betwee…☆30Oct 8, 2026Updated last month
- ⚡️Qwen-Image 4.8x🎉 speedup with Hybrid Acceleration for low VRAM GPUs☆17Oct 24, 2025Updated last year
- 使用 CUDA C++ 实现的 llama 模型推理框架☆64Nov 8, 2024Updated 2 years ago
- 复现 nanovllm并增加注释☆19Jan 27, 2026Updated 9 months ago
- This project can easily test the ncnn model and even deploy ncnn projects on python to speed up☆11Jul 27, 2019Updated 7 years ago
- A Feishu/Lark AI agent bot☆16Feb 27, 2026Updated 8 months ago
- High performance RMSNorm Implement by using SM Core Storage(Registers and Shared Memory)☆31Jan 22, 2026Updated 9 months ago
- ☆32Jul 2, 2025Updated last year
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- parallel_primitiove base on luisacompute☆12Apr 19, 2026Updated 7 months ago
- Flash-Flash KDA: H100-optimized Flash Kimi Delta Attention kernels☆24Jul 24, 2026Updated 3 months ago
- A standalone GEMM kernel for fp16 activation and quantized weight, extracted from FasterTransformer☆96Jun 21, 2026Updated 4 months ago
- Zeta is a lightweight deep learning framework☆24Apr 5, 2026Updated 7 months ago
- ggml学习笔记,ggml是一个机器学习的推理框架☆18Mar 24, 2024Updated 2 years ago
- Muon in Int8 Precision Made Possible☆21Nov 7, 2026Updated last week
- a repo to study TensorRT Plugin☆11Apr 30, 2025Updated last year
- CUDA 12.2 HMM demos☆21Jul 26, 2024Updated 2 years ago
- Unified tracing profiler and visualizer, one timeline from CPU to GPU/HES to in-kernel zones☆152Sep 21, 2026Updated last month
- 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.
- ☆13Oct 11, 2025Updated last year
- ☆11May 21, 2026Updated 5 months ago
- Source codes for paper "BlockFFN: Towards End-Side Acceleration-Friendly Mixture-of-Experts with Chunk-Level Activation Sparsity".☆20Jan 10, 2026Updated 10 months ago
- play gemm with tvm☆91Jul 22, 2023Updated 3 years ago
- FlashTile is a CUDA Tile IR compiler that is compatible with NVIDIA's tileiras, targeting SM70 through SM121 NVIDIA GPUs.☆60Feb 6, 2026Updated 9 months ago
- ☆17Jan 1, 2024Updated 2 years ago
- Linux on RISC-V on FPGA (LOROF): RV64GC Sv39 Quad-Core Superscalar Out-of-Order Virtual Memory CPU☆19Updated this week
Are these results useful?