Change8

b8660

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

Summary

This release focuses heavily on internal refactoring and optimization for ggml-webgpu, including moving away from parameter buffer pools and improving compatibility and stability.

✨ New Features

  • Started work on removing parameter buffer pools in ggml-webgpu.
  • Added timeout back to wait operations and removed synchronous set_tensor/memset_tensor in ggml-webgpu.
  • Moved to unpackf16 for wider compatibility in ggml-webgpu.

🐛 Bug Fixes

  • Fixed stride calculation in ggml-webgpu.
  • Removed a deadlock condition in free_bufs in ggml-webgpu.

Affected Symbols