print cuda or opencl based on what's used

YellowRoseCx · Jul 3, 2023 · cf65429 · cf65429
1 parent 72c16d2
commit cf65429
Show file tree

Hide file tree

Showing 3 changed files with 27 additions and 3 deletions.
diff --git a/otherarch/gptj_v3.cpp b/otherarch/gptj_v3.cpp
@@ -348,7 +348,11 @@ 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));
+ #if defined(GGML_USE_CLBLAST)
  fprintf(stderr, "%s: [opencl] offloading %d layers to GPU\n", __func__, n_gpu);
+ #else
+ fprintf(stderr, "%s: [CUDA] offloading %d layers to GPU\n", __func__, n_gpu);
+ #endif
  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 +377,11 @@ 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);
+ #if defined(GGML_USE_CLBLAST)
+ fprintf(stderr, "%s: [opencl] total VRAM used: %zu MB\n", __func__, vram_total / 1024 / 1024);
+ #else
+ fprintf(stderr, "%s: [CUDA] total VRAM used: %zu MB\n", __func__, vram_total / 1024 / 1024);
+ #endif
  }
  #endif
 

diff --git a/otherarch/mpt_v3.cpp b/otherarch/mpt_v3.cpp
@@ -301,7 +301,11 @@ 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));
+ #if defined(GGML_USE_CLBLAST)
  fprintf(stderr, "%s: [opencl] offloading %d layers to GPU\n", __func__, n_gpu);
+ #else
+ fprintf(stderr, "%s: [CUDA] offloading %d layers to GPU\n", __func__, n_gpu);
+ #endif
  for (int i = 0; i < n_gpu; ++i) {
  const auto & layer = model.layers[i];
  layer.ffn_up_proj->backend = GGML_BACKEND_GPU;
@@ -320,7 +324,11 @@ 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);
+ #if defined(GGML_USE_CLBLAST)
+ fprintf(stderr, "%s: [opencl] total VRAM used: %zu MB\n", __func__, vram_total / 1024 / 1024);
+ #else
+ fprintf(stderr, "%s: [CUDA] total VRAM used: %zu MB\n", __func__, vram_total / 1024 / 1024);
+ #endif
  }
  #endif
 

diff --git a/otherarch/neox_v3.cpp b/otherarch/neox_v3.cpp
@@ -335,7 +335,11 @@ 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));
+ #if defined(GGML_USE_CLBLAST)
  fprintf(stderr, "%s: [opencl] offloading %d layers to GPU\n", __func__, n_gpu);
+ #else
+ fprintf(stderr, "%s: [CUDA] offloading %d layers to GPU\n", __func__, n_gpu);
+ #endif
  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 +358,11 @@ 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);
+ #if defined(GGML_USE_CLBLAST)
+ fprintf(stderr, "%s: [opencl] total VRAM used: %zu MB\n", __func__, vram_total / 1024 / 1024);
+ #else
+ fprintf(stderr, "%s: [CUDA] total VRAM used: %zu MB\n", __func__, vram_total / 1024 / 1024);
+ #endif
  }
  #endif