openxla/xla

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

4499 stars · 911 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

XLA (Accelerated Linear Algebra) is an open-source machine learning compiler that optimizes models from frameworks like PyTorch, TensorFlow, and JAX for high-performance execution. It targets GPUs, CPUs, and ML accelerators across different hardware platforms.

Use cases

• compile PyTorch models for faster GPU execution
• optimize TensorFlow models for ML accelerators
• speed up JAX computations on CPUs and GPUs
• build custom hardware backends for ML frameworks
• debug and integrate new ML frontends with the compiler

When to choose

• you need to optimize ML models across diverse hardware backends
• you are developing or integrating a new ML accelerator
• you use PyTorch, TensorFlow, or JAX and want compiler-driven performance gains

When to avoid

• you just want to use XLA from a framework without contributing to the compiler itself
• you need a simple inference runtime rather than a compiler toolchain

Facets

library · maturity active

compiler machine-learning gpu-computing llm-training machine-learning compilers gpu-computing deep-learning cpp cross-platform xla ml-compiler linear-algebra accelerators openxla linux gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="openxla/xla")