]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
memory : fix kv cache size for hybrid models (#19559)
authorGeorgi Gerganov <redacted>
Fri, 13 Feb 2026 05:36:24 +0000 (07:36 +0200)
committerGitHub <redacted>
Fri, 13 Feb 2026 05:36:24 +0000 (07:36 +0200)
commitbb96bfd36122aa491a4572afe92991ac89942328
treea3fcb500863b30002627c41a5e34e9889cdbd354
parent0644baefde6afc8d2fee8d0ce7770b6485aa4c06
memory : fix kv cache size for hybrid models (#19559)
src/llama-model.cpp