| .. |
|
LlamaConfig.cmake.in
|
095231dfd3
cmake : fix transient definitions in find pkg (#3411)
|
vor 2 Jahren |
|
build-info.cmake
|
b38a16dfcf
cmake : fix issue with version info not getting baked into LlamaConfig.cmake (#3970)
|
vor 2 Jahren |
|
build-info.sh
|
b12fa0d1c1
build : link against build info instead of compiling against it (#3879)
|
vor 2 Jahren |
|
check-requirements.sh
|
04ac0607e9
python : add check-requirements.sh and GitHub workflow (#4585)
|
vor 2 Jahren |
|
compare-llama-bench.py
|
4f56458d34
Python script to compare commits with llama-bench (#4844)
|
vor 2 Jahren |
|
convert-gg.sh
|
25423e9185
scripts : helper convert script
|
vor 2 Jahren |
|
gen-build-info-cpp.cmake
|
b38a16dfcf
cmake : fix issue with version info not getting baked into LlamaConfig.cmake (#3970)
|
vor 2 Jahren |
|
get-flags.mk
|
70f806b821
build : detect host compiler and cuda compiler separately (#4414)
|
vor 2 Jahren |
|
get-pg.sh
|
9a818f7c42
scripts : improve get-pg.sh (#4838)
|
vor 2 Jahren |
|
get-wikitext-2.sh
|
7c2227a197
chmod : make scripts executable (#2675)
|
vor 2 Jahren |
|
qnt-all.sh
|
611363ac79
scripts : add pipefail
|
vor 2 Jahren |
|
run-all-perf.sh
|
611363ac79
scripts : add pipefail
|
vor 2 Jahren |
|
run-all-ppl.sh
|
611363ac79
scripts : add pipefail
|
vor 2 Jahren |
|
server-llm.sh
|
f0e209324a
scripts : add server-llm.sh (#3868)
|
vor 2 Jahren |
|
sync-ggml-am.sh
|
ab62fc3e55
scripts : fix sync order + metal sed
|
vor 2 Jahren |
|
sync-ggml.last
|
64802ec00d
sync : ggml
|
vor 2 Jahren |
|
sync-ggml.sh
|
fe680e3d10
sync : ggml (new ops, tests, backend, etc.) (#4359)
|
vor 2 Jahren |
|
verify-checksum-models.py
|
bedb92b603
scripts : use `/usr/bin/env` in shebang (#3313)
|
vor 2 Jahren |
Georgi Gerganov
64802ec00d
sync : ggml