8000 Added support for GGML_OP_CLAMP in Metal by dave-fl · Pull Request #6662 · ggml-org/llama.cpp · GitHub
[go: up one dir, main page]
Skip to content

Added support for GGML_OP_CLAMP in Metal #6662

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Apr 14, 2024
Merged

Added support for GGML_OP_CLAMP in Metal #6662

Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
369825f
Added support for GGML_OP_CLAMP in Metal
Apr 13, 2024
83e924f
Corrected size
Apr 13, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Prev Previous commit
Corrected size
  • Loading branch information
dave-fl authored and dave-fl committed Apr 13, 2024
commit 83e924f40bdaef2138eaa10c2378a6d76ce4ee92
4 changes: 2 additions & 2 deletions ggml-metal.m
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1163,8 +1163,8 @@ static enum ggml_status ggml_metal_graph_compute(

float min;
float max;
memcpy(&min, dst->op_params, sizeof(float));
memcpy(&max, (float *) dst->op_params + 1, sizeof(float));
memcpy(&min, ((int32_t *) dst->op_params) + 0, sizeof(float));
memcpy(&max, ((int32_t *) dst->op_params) + 1, sizeof(float));

[encoder setComputePipelineState:pipeline];
[encoder setBuffer:id_src0 offset:offs_src0 atIndex:0];
Expand Down
0