HeegyuKim / torch-xla-SPMDLinks
Pytorch/XLA SPMD Test code in Google TPU
☆23Updated last year
Alternatives and similar repositories for torch-xla-SPMD
Users that are interested in torch-xla-SPMD are comparing it to the libraries listed below
Sorting:
- ☆112Updated last year
- some common Huggingface transformers in maximal update parametrization (µP)☆81Updated 3 years ago
- A fast implementation of T5/UL2 in PyTorch using Flash Attention☆105Updated 3 months ago
- Code for Zero-Shot Tokenizer Transfer☆133Updated 6 months ago
- Google TPU optimizations for transformers models☆114Updated 5 months ago
- The simplest, fastest repository for training/finetuning medium-sized GPTs.☆147Updated 2 weeks ago
- The simplest implementation of recent Sparse Attention patterns for efficient LLM inference.☆78Updated last month
- ☆79Updated last year
- Large scale 4D parallelism pre-training for 🤗 transformers in Mixture of Experts *(still work in progress)*☆85Updated last year
- Prune transformer layers☆69Updated last year
- ☆20Updated 2 years ago
- The source code of our work "Prepacking: A Simple Method for Fast Prefilling and Increased Throughput in Large Language Models" [AISTATS …☆59Updated 9 months ago
- Fast, Modern, and Low Precision PyTorch Optimizers☆97Updated this week
- Yet another random morning idea to be quickly tried and architecture shared if it works; to allow the transformer to pause for any amount…☆54Updated last year
- ☆81Updated last year
- Minimal (400 LOC) implementation Maximum (multi-node, FSDP) GPT training☆129Updated last year
- Multipack distributed sampler for fast padding-free training of LLMs☆194Updated 11 months ago
- Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clusters☆128Updated 7 months ago
- Implementation of the Llama architecture with RLHF + Q-learning☆165Updated 5 months ago
- A MAD laboratory to improve AI architecture designs 🧪☆123Updated 6 months ago
- Language models scale reliably with over-training and on downstream tasks☆97Updated last year
- Understand and test language model architectures on synthetic tasks.☆219Updated last month
- ☆127Updated last year
- The evaluation framework for training-free sparse attention in LLMs☆82Updated 3 weeks ago
- ☆81Updated last year
- Griffin MQA + Hawk Linear RNN Hybrid☆87Updated last year
- ☆68Updated last year
- Tiny re-implementation of MDM in style of LLaDA and nano-gpt speedrun☆54Updated 4 months ago
- Simple and efficient pytorch-native transformer training and inference (batched)☆77Updated last year
- Load compute kernels from the Hub☆203Updated this week