From bfeb3471d765abe4d8f1d593f2fa3780f4dee585 Mon Sep 17 00:00:00 2001 From: Concedo <39025047+LostRuins@users.noreply.github.com> Date: Mon, 3 Jul 2023 21:36:42 +0800 Subject: [PATCH] fix typos --- otherarch/gptj_v3.cpp | 4 ++-- otherarch/mpt_v3.cpp | 4 ++-- otherarch/neox_v3.cpp | 4 ++-- 3 files changed, 6 insertions(+), 6 deletions(-) diff --git a/otherarch/gptj_v3.cpp b/otherarch/gptj_v3.cpp index 13f39b6bf..be4ad60da 100644 --- a/otherarch/gptj_v3.cpp +++ b/otherarch/gptj_v3.cpp @@ -348,7 +348,7 @@ ModelLoadResult gptj_model_load(const std::string & fname, gptj_model & model, g const auto & hparams = model.hparams; size_t vram_total = 0; const int n_gpu = std::min(gpulayers, int(hparams.n_layer)); - fprintf(stderr, "%s: [opencl] offloading %d layers to GPU\n", __func__, n_gpu); + fprintf(stderr, "%s: [GPU] offloading %d layers to GPU\n", __func__, n_gpu); for (int i = 0; i < n_gpu; ++i) { const auto & layer = model.layers[i]; layer.c_attn_q_proj_w->backend = GGML_BACKEND_GPU; @@ -373,7 +373,7 @@ ModelLoadResult gptj_model_load(const std::string & fname, gptj_model & model, g ggml_cuda_transform_tensor(layer.c_mlp_proj_w->data,layer.c_mlp_proj_w); vram_total += ggml_nbytes(layer.c_mlp_proj_w); #endif } - fprintf(stderr, "%s: [opencl] total VRAM used: %zu MB\n", __func__, vram_total / 1024 / 1024); + fprintf(stderr, "%s: [GPU] total VRAM used: %zu MB\n", __func__, vram_total / 1024 / 1024); } #endif diff --git a/otherarch/mpt_v3.cpp b/otherarch/mpt_v3.cpp index ef362a051..e4cf99fd7 100644 --- a/otherarch/mpt_v3.cpp +++ b/otherarch/mpt_v3.cpp @@ -301,7 +301,7 @@ bool mpt_model_load(const std::string & fname, mpt_model & model, gpt_vocab & vo const auto & hparams = model.hparams; size_t vram_total = 0; const int n_gpu = std::min(gpulayers, int(hparams.n_layers)); - fprintf(stderr, "%s: [opencl] offloading %d layers to GPU\n", __func__, n_gpu); + fprintf(stderr, "%s: [GPU] offloading %d layers to GPU\n", __func__, n_gpu); for (int i = 0; i < n_gpu; ++i) { const auto & layer = model.layers[i]; layer.ffn_up_proj->backend = GGML_BACKEND_GPU; @@ -320,7 +320,7 @@ bool mpt_model_load(const std::string & fname, mpt_model & model, gpt_vocab & vo ggml_cuda_transform_tensor(layer.c_attn_out_proj_weight->data,layer.c_attn_out_proj_weight); vram_total += ggml_nbytes(layer.c_attn_out_proj_weight); #endif } - fprintf(stderr, "%s: [opencl] total VRAM used: %zu MB\n", __func__, vram_total / 1024 / 1024); + fprintf(stderr, "%s: [GPU] total VRAM used: %zu MB\n", __func__, vram_total / 1024 / 1024); } #endif diff --git a/otherarch/neox_v3.cpp b/otherarch/neox_v3.cpp index 6df5d534b..29b2d06c8 100644 --- a/otherarch/neox_v3.cpp +++ b/otherarch/neox_v3.cpp @@ -335,7 +335,7 @@ ModelLoadResult gpt_neox_model_load(const std::string & fname, gpt_neox_model & const auto & hparams = model.hparams; size_t vram_total = 0; const int n_gpu = std::min(gpulayers, int(hparams.n_layer)); - fprintf(stderr, "%s: [opencl] offloading %d layers to GPU\n", __func__, n_gpu); + fprintf(stderr, "%s: [GPU] offloading %d layers to GPU\n", __func__, n_gpu); for (int i = 0; i < n_gpu; ++i) { const auto & layer = model.layers[i]; layer.c_attn_attn_w->backend = GGML_BACKEND_GPU; @@ -354,7 +354,7 @@ ModelLoadResult gpt_neox_model_load(const std::string & fname, gpt_neox_model & ggml_cuda_transform_tensor(layer.c_mlp_proj_w->data,layer.c_mlp_proj_w); vram_total += ggml_nbytes(layer.c_mlp_proj_w); #endif } - fprintf(stderr, "%s: [opencl] total VRAM used: %zu MB\n", __func__, vram_total / 1024 / 1024); + fprintf(stderr, "%s: [GPU] total VRAM used: %zu MB\n", __func__, vram_total / 1024 / 1024); } #endif