Tutorials
Start from what you are doing. Each tutorial takes one workflow from the code you have to a result you can measure, with every step tested.
- OverviewAccelerate PyTorch
Speed up PyTorch on the CPU with Kwker - pick your workflow - inference, torch.compile, lower precision, training, whole-model runners or operators.
- OverviewAccelerate Hugging Face
Run Hugging Face models faster on the CPU with Kwker - generate text, chat, serve an OpenAI-compatible API, quantize, and embed sentences.
- TutorialClassify images
Classify images on the CPU with KwkCNN - check that a torchvision model is supported, run it in float32, then in int8 calibrated on your own photos.
- How-to guideAccelerate JAX
Sort, argsort, top-k and rank JAX arrays on the CPU with Kwker, inside jit and vmap and with gradients, as XLA custom calls with no host copies.
- OverviewData and analytics
Speed up data work with Kwker - NumPy without code changes, pandas, Polars and pyarrow tables, DuckDB queries, sparse matrices and files larger than memory.
- TutorialRank a leaderboard
Build a game leaderboard in Python - ranks with ties, a sorted table with a tiebreak, and the top three - then check it on a million players.
Examples
Accelerate PyTorch
- Speed up inference with one line
- Compile with torch.compile
- Lower precision with an accuracy check
- Train faster on the CPU
- Sorting operators and layers
- A faster model, step by step
Accelerate Hugging Face
- Generate text with a Hugging Face model
- int8 and int4 weights
- Faster generation
- Chat and serving
- Sentence embeddings
Image models and JAX
Data and analytics
- NumPy drop-in
- DataFrames, Arrow and DuckDB
- Group-by on a table
- ORDER BY in DuckDB
- Sort a file larger than memory
Kwker Core
Kwker in your language
Related
- Quickstarts: install Kwker and get a first result, one page per workflow.
- How-to guides: one task per page, with examples in eight languages.