AI-Hypercomputer / jetstream-pytorch
PyTorch/XLA integration with JetStream (https://github.com/google/JetStream) for LLM inference"
☆41Updated 2 weeks ago
Related projects ⓘ
Alternatives and complementary repositories for jetstream-pytorch
- Google TPU optimizations for transformers models☆75Updated this week
- JetStream is a throughput and memory optimized engine for LLM inference on XLA devices, starting with TPUs (and GPUs in future -- PRs wel…☆236Updated this week
- ☆122Updated this week
- ☆156Updated last week
- Applied AI experiments and examples for PyTorch☆168Updated 3 weeks ago
- extensible collectives library in triton☆72Updated 2 months ago
- A user-friendly tool chain that enables the seamless execution of ONNX models using JAX as the backend.☆98Updated 2 months ago
- ☆177Updated last week
- ☆101Updated last month
- This repository contains the experimental PyTorch native float8 training UX☆212Updated 3 months ago
- 🚀 Efficiently (pre)training foundation models with native PyTorch features, including FSDP for training and SDPA implementation of Flash…☆194Updated this week
- Inference code for LLaMA models in JAX☆113Updated 6 months ago
- 🚀 Collection of components for development, training, tuning, and inference of foundation models leveraging PyTorch native components.☆166Updated this week
- Fast Matrix Multiplications for Lookup Table-Quantized LLMs☆187Updated this week
- ring-attention experiments☆97Updated last month
- ☆153Updated this week
- Simple and fast low-bit matmul kernels in CUDA / Triton☆147Updated this week
- xpk (Accelerated Processing Kit, pronounced x-p-k,) is a software tool to help Cloud developers to orchestrate training jobs on accelerat…☆81Updated this week
- Efficient, Flexible and Portable Structured Generation☆125Updated this week
- seqax = sequence modeling + JAX☆134Updated 4 months ago
- ☆225Updated 4 months ago
- A high-throughput and memory-efficient inference and serving engine for LLMs☆253Updated last month
- A safetensors extension to efficiently store sparse quantized tensors on disk☆51Updated this week
- ☆20Updated last year
- Module, Model, and Tensor Serialization/Deserialization☆189Updated last month
- ☆268Updated this week
- Testing framework for Deep Learning models (Tensorflow and PyTorch) on Google Cloud hardware accelerators (TPU and GPU)☆64Updated 2 months ago
- ☆51Updated 7 months ago
- ☆12Updated last month
- ☆39Updated 10 months ago