]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: b931f81)
CUDA: tune GLM 4.7 Flash FA kernel selection logic (DGX Spark) (#19142)
authorGeorgi Gerganov <redacted>
Wed, 28 Jan 2026 07:15:11 +0000 (09:15 +0200)
committerGitHub <redacted>
Wed, 28 Jan 2026 07:15:11 +0000 (09:15 +0200)
commit2eee6c866c89bcb101693c8b33fa6e1a7f98932c
treeb38e685d7265ecbef17343090d17fc02abd10437tree
parentb931f81b5a3bc3e16bd74cebc8fee8cbd69f8d4dcommit | diff
CUDA: tune GLM 4.7 Flash FA kernel selection logic (DGX Spark) (#19142)
ggml/src/ggml-cuda/common.cuh diff | blob | history
ggml/src/ggml-cuda/fattn.cu diff | blob | history
Packaging of ggml-org/llama.cpp