Skip to content

Commit

Permalink
metal : reduce command encoding overhead
Browse files Browse the repository at this point in the history
ggml-ci
  • Loading branch information
ggerganov committed Oct 1, 2024
1 parent 1927378 commit 43b9d69
Show file tree
Hide file tree
Showing 5 changed files with 1,890 additions and 1,805 deletions.
7 changes: 0 additions & 7 deletions examples/cvector-generator/pca.hpp
Original file line number Diff line number Diff line change
Expand Up @@ -204,13 +204,6 @@ static ggml_status compute_piter(
ggml_backend_cpu_set_n_threads(model.backend, params.n_threads);
}

// TODO: enable GPU support when support for GGML_OP_SQRT is added
//#ifdef GGML_USE_METAL
// if (ggml_backend_is_metal(model.backend)) {
// ggml_backend_metal_set_n_cb(model.backend, params.n_threads);
// }
//#endif

ggml_status res = ggml_backend_graph_compute(model.backend, gf);
if (res == GGML_STATUS_SUCCESS) {
auto extract_i = [](std::string prefix, std::string str) -> int {
Expand Down
6 changes: 0 additions & 6 deletions examples/llava/clip.cpp
Original file line number Diff line number Diff line change
Expand Up @@ -2444,12 +2444,6 @@ bool clip_image_batch_encode(clip_ctx * ctx, const int n_threads, const clip_ima
ggml_backend_cpu_set_n_threads(ctx->backend, n_threads);
}

#ifdef GGML_USE_METAL
if (ggml_backend_is_metal(ctx->backend)) {
ggml_backend_metal_set_n_cb(ctx->backend, n_threads);
}
#endif

ggml_backend_graph_compute(ctx->backend, gf);

// the last node is the embedding tensor
Expand Down
5 changes: 0 additions & 5 deletions ggml/include/ggml-metal.h
Original file line number Diff line number Diff line change
Expand Up @@ -25,9 +25,6 @@
#include <stddef.h>
#include <stdbool.h>

// max memory buffers that can be mapped to the device
#define GGML_METAL_MAX_BUFFERS 64

struct ggml_tensor;
struct ggml_cgraph;

Expand All @@ -48,8 +45,6 @@ GGML_API bool ggml_backend_is_metal(ggml_backend_t backend);

GGML_API GGML_CALL ggml_backend_buffer_t ggml_backend_metal_buffer_from_ptr(void * data, size_t size, size_t max_size);

GGML_API void ggml_backend_metal_set_n_cb(ggml_backend_t backend, int n_cb);

GGML_API void ggml_backend_metal_set_abort_callback(ggml_backend_t backend, ggml_abort_callback abort_callback, void * user_data);

GGML_API GGML_CALL ggml_backend_buffer_type_t ggml_backend_metal_buffer_type(void);
Expand Down
Loading

0 comments on commit 43b9d69

Please sign in to comment.