FlexAttention based, minimal vllm-style inference engine for fast Gemma 2 inference.
☆367Nov 2, 2025Updated last year
Alternatives and similar repositories for flex-nano-vllm
Users that are interested in flex-nano-vllm are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Simple MPI implementation for prototyping or learning☆331Aug 6, 2025Updated last year
- Minimalistic 4D-parallelism distributed training framework for education purpose☆2,346Aug 26, 2025Updated last year
- Implementing DeepSeek R1's GRPO algorithm from scratch☆1,920Apr 18, 2025Updated last year
- Our library for RL environments + evals☆4,793Updated this week
- The simplest, fastest repository for training/finetuning small-sized VLMs.☆5,076Oct 27, 2025Updated last year
- 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.
- Simple Byte pair Encoding mechanism used for tokenization process . written purely in C☆158Nov 11, 2024Updated 2 years ago
- UNet diffusion model in pure CUDA☆668Jun 28, 2024Updated 2 years ago
- A PyTorch native platform for training generative AI models☆5,916Updated this week
- Official repository for our work on micro-budget training of large-scale diffusion models.☆1,603Jan 12, 2025Updated last year
- Frontier Models playing the board game Diplomacy.☆715Jun 1, 2026Updated 5 months ago
- NanoGPT (124M) in 90 seconds☆6,051Sep 28, 2026Updated last month
- Efficient Triton Kernels for LLM Training☆6,705Updated this week
- Implementation of Diffusion Transformer (DiT) in JAX☆323Jun 11, 2024Updated 2 years ago
- Helpful tools and examples for working with flex-attention☆1,267Updated this week
- 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.
- gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI☆20,548Oct 29, 2026Updated 3 weeks ago
- Custom triton kernels for training Karpathy's nanoGPT.☆19Oct 21, 2024Updated 2 years ago
- A subset of PyTorch's neural network modules, written in Python using OpenAI's Triton.☆608Aug 14, 2026Updated 3 months ago
- ☆125May 19, 2025Updated last year
- a minimal cache manager for PagedAttention, on top of llama3.☆151Aug 26, 2024Updated 2 years ago
- Single File, Single GPU, From Scratch, Efficient, Full Parameter Tuning library for "RL for LLMs"☆644Oct 7, 2025Updated last year
- Tile primitives for speedy kernels☆3,803Sep 12, 2026Updated 2 months ago
- Accelerating MoE with IO and Tile-aware Optimizations☆791Aug 29, 2026Updated 2 months ago
- ☆267Nov 24, 2025Updated 11 months ago
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- Fast bare-bones BPE for modern tokenizer training☆181Jun 23, 2025Updated last year
- A compact implementation of SGLang, designed to demystify the complexities of modern LLM serving systems.☆5,609May 17, 2026Updated 6 months ago
- Nano vLLM☆16,466Apr 26, 2026Updated 6 months ago
- Minimal (400 LOC) implementation Maximum (multi-node, FSDP) GPT training☆132Apr 17, 2024Updated 2 years ago
- Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.☆6,273Aug 22, 2025Updated last year
- Radix Tree KV Cache with Turn-Aware Growth☆12Jul 21, 2025Updated last year
- JAX implementation ViT-VQGAN☆68Jul 23, 2022Updated 4 years ago
- ☆37Aug 7, 2025Updated last year
- Minimal reproduction of DeepSeek R1-Zero☆13,258Feb 27, 2026Updated 8 months ago
- 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.
- An implementation of PSGD Kron second-order optimizer for PyTorch☆119Jul 24, 2025Updated last year
- An efficient implementation of the NSA (Native Sparse Attention) kernel☆135Jun 24, 2025Updated last year
- NanoGPT-speedrunning for the poor T4 enjoyers☆72Apr 22, 2025Updated last year
- ☆367Updated this week
- A single-file educational implementation for understanding vLLM's core concepts and running LLM inference.☆47Apr 7, 2026Updated 7 months ago
- Minimal Claude Code alternative. Single Python file, zero dependencies, ~250 lines.☆2,813Jan 14, 2026Updated 10 months ago
- What would you do with 1000 H100s...☆1,205Jan 10, 2024Updated 2 years ago
Are these results useful?