]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
llama : run all KQV ops on the CPU with no KV offload (#5049)
authorslaren <redacted>
Sat, 20 Jan 2024 15:05:49 +0000 (16:05 +0100)
committerGitHub <redacted>
Sat, 20 Jan 2024 15:05:49 +0000 (17:05 +0200)
commit6df465a91d402370bcba6676b19fad85b06ce7e0
tree6d83544d367a9fdad6f1381faef1d42f6fca2375
parent77bc1bbd05f0c31cb45773eb5eb59b9ff2b07e1b
llama : run all KQV ops on the CPU with no KV offload (#5049)

ggml-ci
ggml-backend.c
llama.cpp