]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: e9b66ee)
ggml : force no_alloc == false when creating opt tensors (close #1699)
authorGeorgi Gerganov <redacted>
Sat, 10 Jun 2023 09:06:45 +0000 (12:06 +0300)
committerGeorgi Gerganov <redacted>
Sat, 10 Jun 2023 09:08:15 +0000 (12:08 +0300)
commit17c10acfb44ecb7af25e37fb67b9501cbc0034d2
treea5984f62861aa21d2f3726178a2c1d4330fadbf4tree
parente9b66ee9829039d4ab54550d6222e42a0b31e52acommit | diff
ggml : force no_alloc == false when creating opt tensors (close #1699)

This is needed to make operators like ggml_view() be able to store their
parameters in the ggml context's memory and not get discarded when
no_alloc is true
ggml.c diff | blob | history
Packaging of ggml-org/llama.cpp