]> git.djapps.eu Git - pkg/ggml/sources/ggml/commit
overview / pkg / ggml / sources / ggml / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: e3f630b)
metal : separate scale and mask from QKT in FA kernel (llama/9189)
authorGeorgi Gerganov <redacted>
Mon, 26 Aug 2024 15:31:02 +0000 (18:31 +0300)
committerGeorgi Gerganov <redacted>
Tue, 27 Aug 2024 19:01:14 +0000 (22:01 +0300)
commit51c6f1901b06c09e36d0af77d75d5aa2c390ca40
treefdfe56a90aa75a32fdb98baaac450e3baa257f1dtree
parente3f630b10ea576e1c68579a128809b22e95bd47ecommit | diff
metal : separate scale and mask from QKT in FA kernel (llama/9189)

* metal : separate scale and mask from QKT in FA kernel

* metal : ne01 check no longer necessary

* metal : keep data in local memory
src/ggml-metal.metal diff | blob | history
Packaging of ggml-org/ggml