Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly
Appearance settings

Commit bfeb347

Browse filesBrowse files
LostRuinsLostRuins
committed
fix typos
1 parent 3d2907d commit bfeb347
Copy full SHA for bfeb347

File tree

Expand file treeCollapse file tree

3 files changed

+6
-6
lines changed
Filter options
Expand file treeCollapse file tree

3 files changed

+6
-6
lines changed

‎otherarch/gptj_v3.cpp

Copy file name to clipboardExpand all lines: otherarch/gptj_v3.cpp
+2-2Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -348,7 +348,7 @@ ModelLoadResult gptj_model_load(const std::string & fname, gptj_model & model, g
348348
const auto & hparams = model.hparams;
349349
size_t vram_total = 0;
350350
const int n_gpu = std::min(gpulayers, int(hparams.n_layer));
351-
fprintf(stderr, "%s: [opencl] offloading %d layers to GPU\n", __func__, n_gpu);
351+
fprintf(stderr, "%s: [GPU] offloading %d layers to GPU\n", __func__, n_gpu);
352352
for (int i = 0; i < n_gpu; ++i) {
353353
const auto & layer = model.layers[i];
354354
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
373373
ggml_cuda_transform_tensor(layer.c_mlp_proj_w->data,layer.c_mlp_proj_w); vram_total += ggml_nbytes(layer.c_mlp_proj_w);
374374
#endif
375375
}
376-
fprintf(stderr, "%s: [opencl] total VRAM used: %zu MB\n", __func__, vram_total / 1024 / 1024);
376+
fprintf(stderr, "%s: [GPU] total VRAM used: %zu MB\n", __func__, vram_total / 1024 / 1024);
377377
}
378378
#endif
379379

‎otherarch/mpt_v3.cpp

Copy file name to clipboardExpand all lines: otherarch/mpt_v3.cpp
+2-2Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -301,7 +301,7 @@ bool mpt_model_load(const std::string & fname, mpt_model & model, gpt_vocab & vo
301301
const auto & hparams = model.hparams;
302302
size_t vram_total = 0;
303303
const int n_gpu = std::min(gpulayers, int(hparams.n_layers));
304-
fprintf(stderr, "%s: [opencl] offloading %d layers to GPU\n", __func__, n_gpu);
304+
fprintf(stderr, "%s: [GPU] offloading %d layers to GPU\n", __func__, n_gpu);
305305
for (int i = 0; i < n_gpu; ++i) {
306306
const auto & layer = model.layers[i];
307307
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
320320
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);
321321
#endif
322322
}
323-
fprintf(stderr, "%s: [opencl] total VRAM used: %zu MB\n", __func__, vram_total / 1024 / 1024);
323+
fprintf(stderr, "%s: [GPU] total VRAM used: %zu MB\n", __func__, vram_total / 1024 / 1024);
324324
}
325325
#endif
326326

‎otherarch/neox_v3.cpp

Copy file name to clipboardExpand all lines: otherarch/neox_v3.cpp
+2-2Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -335,7 +335,7 @@ ModelLoadResult gpt_neox_model_load(const std::string & fname, gpt_neox_model &
335335
const auto & hparams = model.hparams;
336336
size_t vram_total = 0;
337337
const int n_gpu = std::min(gpulayers, int(hparams.n_layer));
338-
fprintf(stderr, "%s: [opencl] offloading %d layers to GPU\n", __func__, n_gpu);
338+
fprintf(stderr, "%s: [GPU] offloading %d layers to GPU\n", __func__, n_gpu);
339339
for (int i = 0; i < n_gpu; ++i) {
340340
const auto & layer = model.layers[i];
341341
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 &
354354
ggml_cuda_transform_tensor(layer.c_mlp_proj_w->data,layer.c_mlp_proj_w); vram_total += ggml_nbytes(layer.c_mlp_proj_w);
355355
#endif
356356
}
357-
fprintf(stderr, "%s: [opencl] total VRAM used: %zu MB\n", __func__, vram_total / 1024 / 1024);
357+
fprintf(stderr, "%s: [GPU] total VRAM used: %zu MB\n", __func__, vram_total / 1024 / 1024);
358358
}
359359
#endif
360360

0 commit comments

Comments
0 (0)
Morty Proxy This is a proxified and sanitized view of the page, visit original site.