llama.cpp

d0068583 - ggml-webgpu: move from parameter buffer pool to single buffer with offsets (#21278)

ggml-webgpu: move from parameter buffer pool to single buffer with offsets (#21278) * 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 * Start work on removing parameter buffer pools * Simplify and optimize further * simplify profile futures * Fix stride * Try using a single command buffer per batch * formatting