]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 06938ac)
cuda: reserve space for quantize kv-cache at startup (#23907)
authorAman Gupta <redacted>
Wed, 3 Jun 2026 10:39:59 +0000 (18:39 +0800)
committerGitHub <redacted>
Wed, 3 Jun 2026 10:39:59 +0000 (18:39 +0800)
commitf8f0a47a55167bea25199d4d761372cd7cee76b7
tree27bea280c0dd18ddf3ba8445601b3a6eba92d9cetree
parent06938ac129e5feee1e731323e5c37dc973de5573commit | diff
cuda: reserve space for quantize kv-cache at startup (#23907)

* cuda: reserve space for quantize kv-cache at startup

* address review comments

* remove forward decl

Co-authored-by: Johannes Gäßler <redacted>
* remove assert in ggml-cuda.cu

Co-authored-by: Johannes Gäßler <redacted>
---------

Co-authored-by: Johannes Gäßler <redacted>
ggml/src/ggml-cuda/fattn-common.cuh diff | blob | history
ggml/src/ggml-cuda/fattn.cu diff | blob | history
ggml/src/ggml-cuda/fattn.cuh diff | blob | history
ggml/src/ggml-cuda/ggml-cuda.cu diff | blob | history
Packaging of ggml-org/llama.cpp