Pinned Repositories
bess-kge
A PyTorch library for Knowledge Graph Embedding on Graphcore IPUs implementing the distribution framework BESS
gfloat
Generic floating-point types in Python
jax-experimental
JAX for Graphcore IPU (experimental)
jax-scalify
JAX Scalify: end-to-end scaled arithmetics
llm-inference-research
An experimentation platform for LLM inference optimisation
mess
MESS: Modern Electronic Structure Simulations
out-of-the-box-fp8-training
Demo of the unit_scaling library, showing how a model can be easily adapted to train in FP8.
pyscf-ipu
PySCF on IPU
unit-scaling
A library for unit scaling in PyTorch
unit-scaling-demo
Unit Scaling demo and experimentation code
Graphcore Research's Repositories
graphcore-research/unit-scaling
A library for unit scaling in PyTorch
graphcore-research/out-of-the-box-fp8-training
Demo of the unit_scaling library, showing how a model can be easily adapted to train in FP8.
graphcore-research/pyscf-ipu
PySCF on IPU
graphcore-research/llm-inference-research
An experimentation platform for LLM inference optimisation
graphcore-research/minimol
MiniMol is a 10M-parameters molecular fingerprinting model pre-trained on >3300 biological and quantum tasks
graphcore-research/jax-experimental
JAX for Graphcore IPU (experimental)
graphcore-research/mess
MESS: Modern Electronic Structure Simulations
graphcore-research/jax-scalify
JAX Scalify: end-to-end scaled arithmetics
graphcore-research/unit-scaling-demo
Unit Scaling demo and experimentation code
graphcore-research/gfloat
Generic floating-point types in Python
graphcore-research/tessellate-ipu
TessellateIPU: low level Poplar tile programming from Python
graphcore-research/kg-topology-toolbox
A Python toolbox to compute topological metrics and statistics for Knowledge Graphs
graphcore-research/track-and-visualize
Track & Visualisation tool for numerics debugging
graphcore-research/bess-kge
A PyTorch library for Knowledge Graph Embedding on Graphcore IPUs implementing the distribution framework BESS
graphcore-research/flash-attention-ipu
Poplar implementation of FlashAttention for IPU
graphcore-research/graphcore-research.github.io
graphcore-research/ipu-ray-lib
Path-tracer with Neural HDRI for Graphcore IPUs.
graphcore-research/pytorch-approx-topk
Bucketed top-k for PyTorch using a priority queue
graphcore-research/sparq-gpt-fast
Fork of pytorch-labs/gpt-fast with SparQ attention and benchmarking
graphcore-research/notebooks
Small, standalone, machine learning & IPU notebooks
graphcore-research/sparq-llama.cpp
LLM inference in C/C++
graphcore-research/sparsity-benchmarks
Benchmarking code for “PopSparse: Accelerated block sparse matrix multiplication on IPU”
graphcore-research/arith25-stochastic-rounding
Support materials for "On Stochastic Rounding with Few Random Bits", Fitzgibbon and Felix, ARITH 2025
graphcore-research/graphium-smg
Graphium fork for Scaling Molecular GNNs project at Graphcore
graphcore-research/torchtitan-fork
A PyTorch native library for large model training
graphcore-research/ao-fork
PyTorch native quantization and sparsity for training and inference
graphcore-research/coconut
Training Large Language Model to Reason in a Continuous Latent Space
graphcore-research/HolisticTraceAnalysis-fork
A library to analyze PyTorch traces.
graphcore-research/ml_dtypes
A stand-alone implementation of several NumPy dtype extensions used in machine learning.
graphcore-research/open-r1
Fully open reproduction of DeepSeek-R1