Skip to content

metal : fix build and some more comments#10229

Merged
ggerganov merged 1 commit intomasterfrom
gg/metal-fix-build
Nov 9, 2024
Merged

metal : fix build and some more comments#10229
ggerganov merged 1 commit intomasterfrom
gg/metal-fix-build

Conversation

@ggerganov
Copy link
Copy Markdown
Member

@ggerganov ggerganov commented Nov 9, 2024

fix #10208
cont #10171

This is the relevant change for the build fix:

typedef decltype(kernel_flash_attn_ext_vec<FA_TYPES, half4x4, 1, dequantize_f16, half4x4, 1, dequantize_f16, 128>) flash_attn_ext_vec_t;

The FA vec implementation currently requires D%128 == 0.

@ggerganov ggerganov merged commit 39a334a into master Nov 9, 2024
arthw pushed a commit to arthw/llama.cpp that referenced this pull request Nov 15, 2024
arthw pushed a commit to arthw/llama.cpp that referenced this pull request Nov 18, 2024
Seunghhon pushed a commit to Seunghhon/llama.cpp that referenced this pull request Apr 26, 2026
ljubomirj pushed a commit to ljubomirj/llama.cpp that referenced this pull request May 6, 2026
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

Bug: ggml_metal_init error: zero-length arrays are not permitted in C++ float4x4 lo[D16/NW4];

1 participant