Change8

b9564

📦 llama-cppView on GitHub →
2 features🐛 2 fixes🔧 1 symbols

Summary

This release focuses on performance improvements for WebGPU by implementing 2D workgroups for core operations and includes various platform-specific binary releases.

✨ New Features

  • Implemented 2D workgroups for scale, binary, and unary operations in ggml-webgpu.
  • Added webgpu only CI workflow.

🐛 Bug Fixes

  • Fixed a type issue.
  • Moved back to using global_invocation_id in ggml-webgpu implementation.

Affected Symbols