From 5656d10599bd756dc0f17284e418e704200b43f3 Mon Sep 17 00:00:00 2001
From: Evan Miller <emmiller@gmail.com>
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 <ggerganov@gmail.com>
---
 CMakeLists.txt | 24 ++++++++++++++++++++++++
 1 file changed, 24 insertions(+)

(limited to 'CMakeLists.txt')

diff --git a/CMakeLists.txt b/CMakeLists.txt
index eed7b1b..cf6cd34 100644
--- a/CMakeLists.txt
+++ b/CMakeLists.txt
@@ -75,6 +75,7 @@ option(LLAMA_CUDA_DMMV_F16                   "llama: use 16 bit floats for dmmv
 set(LLAMA_CUDA_KQUANTS_ITER "2" CACHE STRING "llama: iters./thread per block for Q2_K/Q6_K")
 option(LLAMA_CLBLAST                         "llama: use CLBlast"                               OFF)
 option(LLAMA_METAL                           "llama: use Metal"                                 OFF)
+option(LLAMA_MPI                             "llama: use MPI"                                   OFF)
 option(LLAMA_K_QUANTS                        "llama: use k-quants"                              ON)
 option(LLAMA_QKK_64                          "llama: use super-block size of 64 for k-quants"   OFF)
 
@@ -308,6 +309,28 @@ if (LLAMA_METAL)
         )
 endif()
 
+if (LLAMA_MPI)
+    cmake_minimum_required(VERSION 3.10)
+    find_package(MPI)
+    if (MPI_C_FOUND)
+        message(STATUS "MPI found")
+        set(GGML_SOURCES_MPI ggml-mpi.c ggml-mpi.h)
+        add_compile_definitions(GGML_USE_MPI)
+        add_compile_definitions(${MPI_C_COMPILE_DEFINITIONS})
+        set(cxx_flags ${cxx_flags} -Wno-cast-qual)
+        set(c_flags   ${c_flags}   -Wno-cast-qual)
+        set(LLAMA_EXTRA_LIBS     ${LLAMA_EXTRA_LIBS}     ${MPI_C_LIBRARIES})
+        set(LLAMA_EXTRA_INCLUDES ${LLAMA_EXTRA_INCLUDES} ${MPI_C_INCLUDE_DIRS})
+        # Even if you're only using the C header, C++ programs may bring in MPI
+        # C++ functions, so more linkage is needed
+        if (MPI_CXX_FOUND)
+            set(LLAMA_EXTRA_LIBS ${LLAMA_EXTRA_LIBS}     ${MPI_CXX_LIBRARIES})
+        endif()
+    else()
+        message(WARNING "MPI not found")
+    endif()
+endif()
+
 if (LLAMA_CLBLAST)
     find_package(CLBlast)
     if (CLBlast_FOUND)
@@ -476,6 +499,7 @@ add_library(ggml OBJECT
             ${GGML_SOURCES_CUDA}
             ${GGML_SOURCES_OPENCL}
             ${GGML_SOURCES_METAL}
+            ${GGML_SOURCES_MPI}
             ${GGML_SOURCES_EXTRA}
             )
 
-- 
cgit v1.2.3