From 4760e7cc0b68570d58f55e8dda469805d1759d0d Mon Sep 17 00:00:00 2001 From: Georgi Gerganov Date: Mon, 13 Nov 2023 14:16:23 +0200 Subject: sync : ggml (backend v2) (#3912) * sync : ggml (backend v2) (wip) * sync : migrate examples and llama.cpp to dynamic graphs (wip) * sync : update tests + fix max op params to 64 ggml-ci * sync : ggml-cuda ggml-ci * llama : fix save/load state context size ggml-ci * sync : try to fix build on tvOS * sync : pass custom graph sizes in training examples * sync : update graph copies to new ggml API * sync : update sync-ggml.sh with new files * scripts : fix header in sync script * train : fix context size calculations * llama : increase inference graph size up to 4096 nodes * train : allocate grads for backward graphs * train : allocate grads for gb_tmp --- common/train.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'common/train.h') diff --git a/common/train.h b/common/train.h index d86c93cc..263d940c 100644 --- a/common/train.h +++ b/common/train.h @@ -9,6 +9,8 @@ #include "ggml.h" #include "llama.h" +#define LLAMA_TRAIN_MAX_NODES 16384 + typedef std::string mt19937_state; struct train_state { -- cgit v1.2.3