ggml-rpc: chunk send()/recv() to avoid EINVAL for very large tensors over RPC (macOS & others) (llama/15188)

ggml : fix field name when new ggml_backend (llama/14944)

rpc : check for null buffers in get/set/copy tensor endpoints (llama/14868)

rpc : nicer error messages for RPC server crash (llama/14076)

rpc : add rpc_msg_set_tensor_hash_req (llama/13353)

rpc : use backend registry, support dl backends (llama/13304)

rpc : avoid uninitialized memory in serialize_tensor (llama/13210)

fix(rpc): Improve input validation and error handling (llama/13069)

rpc : do not wait for response when sending RPC_CMD_SET_TENSOR (llama/12943)

rpc : add RPC_CMD_HELLO (llama/12955)

rpc : use ggml_context_ptr (llama/12938)

rpc : send hash when tensor data is above some fixed threshold (llama/12496)

ggml : upgrade init_tensor API to return a ggml_status (llama/11854)

rpc: fix known RCE in rpc-server (ggml/1103)

rpc : better caching of the base buffer pointer (llama/11331)

rpc : code cleanup (llama/11107)

Support for models with non-512-aligned tensors over RPC. (llama/11047)

ggml : add support for dynamic loading of backends (llama/10469)

ggml : build backends as libraries (llama/10256)