Back to feed

b8607

Apr 1, 2026
Meta/llama.cppCLIvb8607

ggml webgpu: quantized buffers to u32 + wider browser/device support (#21046)

  • Work towards removing bitcast

  • Move rest of existing types over

  • Add timeout back to wait and remove synchronous set_tensor/memset_tensor

  • move to unpackf16 for wider compatibility

  • cleanup

  • Remove deadlock condition in free_bufs

macOS/iOS:

Linux:

Windows:

openEuler: