Noumena-Network / nmoeLinks
MoE training for Me and You and maybe other people
☆331Updated 3 weeks ago
Alternatives and similar repositories for nmoe
Users that are interested in nmoe are comparing it to the libraries listed below
Sorting:
- NanoGPT-speedrunning for the poor T4 enjoyers☆73Updated 9 months ago
- Storing long contexts in tiny caches with self-study☆231Updated last month
- an open source reproduction of NVIDIA's nGPT (Normalized Transformer with Representation Learning on the Hypersphere)☆109Updated 10 months ago
- seqax = sequence modeling + JAX☆170Updated 6 months ago
- Simple Transformer in Jax☆142Updated last year
- DeMo: Decoupled Momentum Optimization☆198Updated last year
- Repo for "LoLCATs: On Low-Rank Linearizing of Large Language Models"☆251Updated last year
- ☆92Updated last year
- SIMD quantization kernels☆94Updated 4 months ago
- supporting pytorch FSDP for optimizers☆84Updated last year
- FlexAttention based, minimal vllm-style inference engine for fast Gemma 2 inference.☆333Updated 2 months ago
- ☆116Updated last week
- The simplest, fastest repository for training/finetuning medium-sized GPTs.☆186Updated last week
- Normalized Transformer (nGPT)☆197Updated last year
- Dion optimizer algorithm☆420Updated 2 weeks ago
- Attention Kernels for Symmetric Power Transformers☆128Updated 4 months ago
- Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clusters☆131Updated last year
- PCCL (Prime Collective Communications Library) implements fault tolerant collective communications over IP☆141Updated 4 months ago
- Understand and test language model architectures on synthetic tasks.☆251Updated 2 weeks ago
- NSA Triton Kernels written with GPT5 and Opus 4.1☆70Updated 5 months ago
- Minimal (400 LOC) implementation Maximum (multi-node, FSDP) GPT training☆132Updated last year
- A set of Python scripts that makes your experience on TPU better☆55Updated 4 months ago
- rl from zero pretrain, can it be done? yes.☆286Updated 4 months ago
- Simple & Scalable Pretraining for Neural Architecture Research☆307Updated last month
- Long context evaluation for large language models☆225Updated 10 months ago
- Quantized LLM training in pure CUDA/C++.☆233Updated last week
- The Automated LLM Speedrunning Benchmark measures how well LLM agents can reproduce previous innovations and discover new ones in languag…☆127Updated 3 months ago
- smolLM with Entropix sampler on pytorch☆149Updated last year
- A MAD laboratory to improve AI architecture designs 🧪☆135Updated last year
- train with kittens!☆63Updated last year