]> git.djapps.eu Git - pkg/ggml/sources/ggml/commit
kv-cache : support V-less cache (llama/19067)
authorGeorgi Gerganov <redacted>
Sun, 25 Jan 2026 13:48:56 +0000 (15:48 +0200)
committerGeorgi Gerganov <redacted>
Fri, 30 Jan 2026 11:49:29 +0000 (13:49 +0200)
commitfce2ea41b8c2b9bfd59a6f228c1fb9ca4c56f71e
treeea9e0a75b9b65e73dc801f72eb26a1a1ccaf2748
parent0c3811643525f3d8597f537b8fe29313082665ba
kv-cache : support V-less cache (llama/19067)

* kv-cache : support V-less cache

* cuda : better check for V_is_K_view

* cuda : improve V_is_K_view check

* graph : add comments

* hparams : refactor
src/ggml-cuda/fattn-common.cuh
src/ggml-cuda/fattn.cu