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

Merged

Commits

ggml-rpc: chunk send()/recv() to avoid EINVAL for very large tensors over RPC (macOS & others). Fixes #15055

Shinnosuke Takagi committed 139 days ago
ggml-rpc: rename RPC_IO_CHUNK->MAX_CHUNK_SIZE, use std::min() for cap, switch to GGML_LOG_ERROR, handle 0-length send/recv

Tak-RS committed 137 days ago
rpc: drop n==0 special case in send_data(); retry in loop per review

Tak-RS committed 136 days ago
rpc: remove trailing whitespace in send_data()

Tak-RS committed 135 days ago