diff options
| author | Kawrakow <48489457+ikawrakow@users.noreply.github.com> | 2024-07-27 07:55:01 +0200 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2024-07-27 07:55:01 +0200 |
| commit | 154e0d75fccf1784fe9ff6fd76a630b66563da3d (patch) | |
| tree | 81ce6dbb5b1900c1aa78a879f0593c694cab9d27 /scripts/compare-commits.sh | |
| parent | 0684c3e9c70d49323b4fc517128cbe222cab7f96 (diff) | |
Merge mainline llama.cpp (#3)
* Merging mainline - WIP
* Merging mainline - WIP
AVX2 and CUDA appear to work.
CUDA performance seems slightly (~1-2%) lower as it is so often
the case with llama.cpp/ggml after some "improvements" have been made.
* Merging mainline - fix Metal
* Remove check
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Diffstat (limited to 'scripts/compare-commits.sh')
| -rwxr-xr-x | scripts/compare-commits.sh | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/scripts/compare-commits.sh b/scripts/compare-commits.sh index a45cd396..70679f4e 100755 --- a/scripts/compare-commits.sh +++ b/scripts/compare-commits.sh @@ -12,7 +12,7 @@ bench_args="${@:3}" rm -f llama-bench.sqlite > /dev/null -# to test a backend, call the script with the corresponding environment variable (e.g. LLAMA_CUDA=1 ./scripts/compare-commits.sh ...) +# to test a backend, call the script with the corresponding environment variable (e.g. GGML_CUDA=1 ./scripts/compare-commits.sh ...) git checkout $1 > /dev/null make clean > /dev/null |