llama.cpp
ggml-cpu: handle 3d tensors in repack mat_mul
#17241
Merged

ggml-cpu: handle 3d tensors in repack mat_mul #17241

Alcpz
Alcpz ggml-cpu: handle 3d tensors in repack mul_mat
950671dc
Alcpz Removed unnecessary branch, removed need for <algorithm>
0b866511
Alcpz Fixed dst_ptr pointer in chunk + clang_format
75c7fd5d
Alcpz GGML_ASSERT to check wdata within bounds
edb7f630
Alcpz Accidental ggml.h inclusion
b56d0ace
Alcpz Improved GGML_ASSERT on wdata boundaries
d1938adb
Alcpz Address performance regression in Qwen and llama.cpp due to chunking
c77bafd8
Alcpz
Alcpz Alcpz changed the title Alcpz/batched repack mul mat ggml-cpu: handle 3d tensors in repack mat_mul 35 days ago
max-krasnyansky
max-krasnyansky max-krasnyansky marked this pull request as ready for review 35 days ago
max-krasnyansky max-krasnyansky requested a review from ggerganov ggerganov 35 days ago
max-krasnyansky max-krasnyansky requested a review from slaren slaren 35 days ago
max-krasnyansky
max-krasnyansky approved these changes on 2025-11-13
Alcpz
max-krasnyansky
github-actions github-actions added ggml
max-krasnyansky max-krasnyansky merged becc4816 into master 35 days ago
Alcpz Alcpz deleted the Alcpz/batched_repack_mul_mat branch 22 days ago

Login to write a write a comment.

Login via GitHub

Assignees
No one assigned
Labels
Milestone