]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
server : don't overfill the batch during infill (#10018)
authorGeorgi Gerganov <redacted>
Mon, 28 Oct 2024 06:49:32 +0000 (08:49 +0200)
committerGitHub <redacted>
Mon, 28 Oct 2024 06:49:32 +0000 (08:49 +0200)
commit8125e6cbfcf2b3b9066e4d923aca9295526730f5
tree81b3f7814ca2d3e947c41e9e48c88fc4c1faa124
parent8841ce3f439de6e770f70319b7e08b6613197ea7
server : don't overfill the batch during infill (#10018)

ggml-ci
examples/server/server.cpp
examples/server/utils.hpp