A PyTorch implementation of the GPT-OSS-20B architecture. All components are coded from scratch: RoPE with YaRN, RMSNorm, SwiGLU with clamping and residual connection, Mixture-of-Experts (MoE), Self-Attention with learned sinks, banded attention, GQA, and KV-cache.
☆238Dec 2, 2025Updated 11 months ago
Alternatives and similar repositories for gpt-oss-20B
Users that are interested in gpt-oss-20B 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 collection of my from-scratch implementation of various models deployed on HF Spaces☆14Oct 14, 2025Updated last year
- Powerful Asynchronous Multi agent framework built from scratch in python supporting RAG and MCP compatibilities.☆12Aug 26, 2025Updated last year
- A series of high-performance GEMM (General Matrix Multiply) implementations Iteratively optimised for H100 GPUs in Pure CUDA.☆84Feb 18, 2026Updated 8 months ago
- ☆19Mar 3, 2025Updated last year
- Course on Flash-attention in Triton☆103Feb 9, 2026Updated 8 months 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.
- Qwen3-0.6B megakernel: 527 tok/s decode on RTX 3090 (3.8x faster than PyTorch)☆145Feb 10, 2026Updated 8 months ago
- A GPT-2 inference engine written from scratch in CUDA and C++. Implements custom CUDA kernels for tiled matrix multiplication, LayerNorm,…☆44May 17, 2026Updated 5 months ago
- Kernels by MakoraGenerate☆15May 26, 2026Updated 5 months ago
- Companion code for The Physics of LLM Inference book☆30Apr 21, 2026Updated 6 months ago
- ☆19Mar 29, 2026Updated 7 months ago
- Pure Triton kernels for Qwen3.5-27B inference on NVIDIA B200☆125Feb 28, 2026Updated 8 months ago
- ☆14Aug 7, 2026Updated 2 months ago
- ☆45May 4, 2025Updated last year
- we have ai at home☆120Jun 18, 2026Updated 4 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.
- a personal collection of my notes for ml sys☆127Oct 26, 2026Updated last week
- Row-wise block scaling for fp8 quantization matrix multiplication. Solution to GPU mode AMD challenge.☆19Feb 9, 2026Updated 8 months ago
- A curated resource list for learning AI performance engineering, from GPU fundamentals to production inference.☆4,320Oct 17, 2026Updated 2 weeks ago
- Pure JavaScript flexbox layout engine — Yoga-compatible API, 2.5x faster initial layout, 5.5x faster re-layout, zero WASM☆17Updated this week
- coding CUDA everyday!☆78Feb 5, 2026Updated 8 months ago
- OpenAnime için WebGPU destekli gayriresmi Linux istemcisi☆17Oct 11, 2026Updated 3 weeks ago
- ☆24Jul 20, 2026Updated 3 months ago
- Plug-and-play PyTorch transformer research framework. Swap attention, FFN, norm, positional, connection, projection, optimizer, scheduler…☆18Oct 25, 2026Updated last week
- Jikan-parity anime/manga REST API on Cloudflare Workers - MyAnimeList data at the edge with D1 caching☆21Oct 13, 2026Updated 3 weeks 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.
- A self-study for CUDA principles from 0 to 1☆20Jan 23, 2026Updated 9 months ago
- ☆134Dec 9, 2025Updated 10 months ago
- mHC kernels implemented in CUDA☆267Mar 9, 2026Updated 7 months ago
- Speed-of-Light SW efficiency by using ultra low-latency primitives for comms collectives☆13Apr 8, 2026Updated 6 months ago
- 🌱 A little course on Reinforcement Learning Environments for evaluating and training Language Models☆242May 27, 2026Updated 5 months ago
- An extension of the nanoGPT repository for training small MOE models.☆291Mar 9, 2025Updated last year
- SQL-like query language and CLI for Qdrant vector search engine☆48Jun 13, 2026Updated 4 months ago
- a whirlwind tour to deep learning alchemy and deep learning systems☆95Updated this week
- documenting my work in inference engineering☆25Apr 19, 2026Updated 6 months 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.
- a fun and educational take on vLLM☆231Jan 25, 2026Updated 9 months ago
- a LLM inference engine to run on consumer hardware☆49Apr 15, 2026Updated 6 months ago
- 100 days of LLM inference engineering — daily posts, experiments, and visualizations☆1,902Apr 30, 2026Updated 6 months ago
- RVAA: Recursive Vision-Action Agent for Long Video Understanding. Implementation of the RLM paradigm (Zhang, Kraska, Khattab 2025)☆118Jan 15, 2026Updated 9 months ago
- Hand-Rolled GPU communications library☆95Nov 25, 2025Updated 11 months ago
- A compact implementation of SGLang, designed to demystify the complexities of modern LLM serving systems.☆5,498May 17, 2026Updated 5 months ago
- ☆35Nov 11, 2025Updated 11 months ago