A compact, readable PyTorch reference implementation of the DeepSeek-V4 architecture (Flash and Pro), in the spirit of nanoGPT. ~4,300 LOC.
☆19Aug 14, 2026Updated 3 months ago
Alternatives and similar repositories for nano-deepseek-v4
Users that are interested in nano-deepseek-v4 are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆12May 11, 2025Updated last year
- ☆13Mar 24, 2024Updated 2 years ago
- Using PDFPlumber for PDF data extraction☆15May 31, 2017Updated 9 years ago
- Slowdown prediction module of Echo: Simulating Distributed Training at Scale☆13Jul 11, 2026Updated 4 months ago
- MachGen's VC attention (https://arxiv.org/html/2609.15810v1) implementation. 2x faster (compared to 1.47-1.6x in original paper) FP8 atte…☆16Oct 12, 2026Updated last month
- 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.
- download and load SA-1B☆11Apr 15, 2023Updated 3 years ago
- ☆14Jun 16, 2025Updated last year
- LP_Bench☆18Feb 27, 2026Updated 8 months ago
- PipeWeave: Synergizing Analytical and Learning Models for Unified GPU Performance Prediction☆23Sep 2, 2026Updated 2 months ago
- Very small and high performance CPU☆13Dec 3, 2024Updated last year
- IntelliJ ExcelReader Plugin☆12Aug 8, 2024Updated 2 years ago
- ☆14Dec 12, 2025Updated 11 months ago
- Dynamo Workshop☆19Nov 7, 2025Updated last year
- Simulating Distributed Training at Scale☆18Sep 15, 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.
- RocksDB/LevelDB inspired key-value database in Go☆10Nov 3, 2020Updated 6 years ago
- Rust implementation of Google protocol buffers☆12Oct 20, 2025Updated last year
- ☆12Dec 30, 2024Updated last year
- AI Hedge Fund Repo integrate with DeepSeek V3 and R1 hosted on SiliconFlow.☆14Feb 3, 2025Updated last year
- Source Code for the Paper: "Channel Charting-Based Channel Prediction on Real-World Distributed Massive MIMO CSI"☆12Apr 9, 2026Updated 7 months ago
- 8-bit RISC Processor on Logisim☆14Oct 1, 2020Updated 6 years ago
- An RTL-level, Chipyard-compatible DRAM simulator model for high fidelity memory simulations.☆13Updated this week
- A mini reproduction of deepseek v4☆12Jul 21, 2026Updated 3 months ago
- The training framework of PCMind-2.1-Kaiyuan-2B built on MindFormers☆15Dec 9, 2025Updated 11 months ago
- 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.
- CUDA+PTX Microbenchmark for RTX 4070 GPU☆11Mar 9, 2026Updated 8 months ago
- ☆15Mar 11, 2026Updated 8 months ago
- A small 6502 system build on a Lattice Icestick FPGA development board☆16Jun 24, 2019Updated 7 years ago
- 目标是在自制虚拟 GPU 上运行 Qwen2-0.5B INT8 推理。核心痛点是从零实现一个类 CUDA 的执行环境——包括 RISC-V SIMT 解释器、PCI 驱动、用户态运行时库和算子库，全部从无到有手写。☆19May 31, 2026Updated 5 months ago
- CUDA Opt Agent is an LLM-driven toolkit for automated CUDA kernel optimization. It generates baselines from text, specs, or existing .cu …☆14Sep 6, 2026Updated 2 months ago
- Booksie: an open catalog of free picture storybooks for children instantly available for reading.☆24Feb 27, 2026Updated 8 months ago
- OK:iCE40Pro, based on iCE40up5k FPGA Core, is an Open Source Educational FPGA GamePad Console.☆16May 6, 2023Updated 3 years ago
- Nano vLLM Triton☆14Aug 27, 2025Updated last year
- MiniLM (BERT) embeddings from scratch☆22Aug 14, 2025Updated last year
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- NetOpsBench: Open Arena for Agentic NetOps in AI Infrastructure☆36Updated this week
- 北京理工大学大四小学期计算机组成原理部分☆12Sep 24, 2020Updated 6 years ago
- Minimal FPGA Processor Core for Stack-based CPU for CPLDs Using Bit-Serial Architecture☆18Sep 6, 2013Updated 13 years ago
- Minimal microprocessor☆21Jul 1, 2017Updated 9 years ago
- A command-line tool to plot roofline models for NVIDIA GPU kernels from profiler output.☆16Oct 15, 2026Updated 3 weeks ago
- ☆26Oct 29, 2026Updated 2 weeks ago
- Pytorch process group third-party plugin for UCC☆22Apr 15, 2024Updated 2 years ago
Are these results useful?