]> git.djapps.eu Git - pkg/ggml/sources/ggml/commit
cpu: introduce chunking for repack matmuls and enable matmul-id chunking on ARM64...
authorMax Krasnyansky <redacted>
Thu, 30 Oct 2025 16:06:13 +0000 (09:06 -0700)
committerGeorgi Gerganov <redacted>
Sat, 1 Nov 2025 07:41:35 +0000 (09:41 +0200)
commitbf545378471b6623fe4a330465364f5f59da3618
tree6479fded6fabc3f409238342fdbacb01b468e578
parentfd33b4bb05d99c0784892a8f4e38d4c7a4d873e3
cpu: introduce chunking for repack matmuls and enable matmul-id chunking on ARM64 (llama/16833)

Very similar implementation to the flash-attention chunking, with similar benefits.
src/ggml-cpu/ggml-cpu.c
src/ggml-cpu/repack.cpp