From 5656d10599bd756dc0f17284e418e704200b43f3 Mon Sep 17 00:00:00 2001 From: Evan Miller Date: Mon, 10 Jul 2023 11:49:56 -0400 Subject: mpi : add support for distributed inference via MPI (#2099) * MPI support, first cut * fix warnings, update README * fixes * wrap includes * PR comments * Update CMakeLists.txt * Add GH workflow, fix test * Add info to README * mpi : trying to move more MPI stuff into ggml-mpi (WIP) (#2099) * mpi : add names for layer inputs + prep ggml_mpi_graph_compute() * mpi : move all MPI logic into ggml-mpi Not tested yet * mpi : various fixes - communication now works but results are wrong * mpi : fix output tensor after MPI compute (still not working) * mpi : fix inference * mpi : minor * Add OpenMPI to GH action * [mpi] continue-on-error: true * mpi : fix after master merge * [mpi] Link MPI C++ libraries to fix OpenMPI * tests : fix new llama_backend API * [mpi] use MPI_INT32_T * mpi : factor out recv / send in functions and reuse * mpi : extend API to allow usage with outer backends (e.g. Metal) --------- Co-authored-by: Georgi Gerganov --- llama.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'llama.h') diff --git a/llama.h b/llama.h index c1e7dab..686463a 100644 --- a/llama.h +++ b/llama.h @@ -158,7 +158,9 @@ extern "C" { // Initialize the llama + ggml backend // If numa is true, use NUMA optimizations // Call once at the start of the program - LLAMA_API void llama_init_backend(bool numa); + LLAMA_API void llama_backend_init(bool numa); + // Call once at the end of the program - currently only used for MPI + LLAMA_API void llama_backend_free(); LLAMA_API int64_t llama_time_us(); -- cgit v1.2.3