]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 1dfbf2c)
sycl : Overcoming workaround for mmap() allocation on Windows (#13482)
authorNicolò Scipione <redacted>
Tue, 20 May 2025 00:54:43 +0000 (02:54 +0200)
committerGitHub <redacted>
Tue, 20 May 2025 00:54:43 +0000 (08:54 +0800)
commitf7c9429c85748cde9599499601ba48d0057722e6
tree18ea499aea78f5561efd4cd32b281c64e8ad4f8btree
parent1dfbf2cf3a9f15193dd893396d07762bbd2c4785commit | diff
sycl : Overcoming workaround for mmap() allocation on Windows (#13482)

* Remove mmap workaround on windows

After some testing I found that mmap is supported on windows and for
many GPUs on Linux. Therefore I remove the workaround for windows since
it is not necessary.

* Update llama-bench README

SYCL backend introduced a workaround that allows execution of
llama-bench also without specifying `--mmp 0` flag
ggml/src/ggml-sycl/ggml-sycl.cpp diff | blob | history
tools/llama-bench/README.md diff | blob | history
Packaging of ggml-org/llama.cpp