| .. |
|
apple
|
e9b6350e61
scripts : make the shell scripts cross-platform (#14341)
|
hai 6 meses |
|
jinja
|
9e2b1e83c6
scripts : add Jinja tester PySide6 simple app (#15756)
|
hai 4 meses |
|
snapdragon
|
c45f89d551
ggml-hexagon: mm for mtmd (#17894)
|
hai 1 mes |
|
bench-models.sh
|
7fd205a8e8
scripts : add script to bench models (#16894)
|
hai 2 meses |
|
build-info.sh
|
f3f65429c4
llama : reorganize source code + improve CMake (#8006)
|
hai 1 ano |
|
check-requirements.sh
|
e9b6350e61
scripts : make the shell scripts cross-platform (#14341)
|
hai 6 meses |
|
compare-commits.sh
|
55042b3692
scripts: add sqlite3 check for compare-commits.sh (#15633)
|
hai 4 meses |
|
compare-llama-bench.py
|
3d16b29c3b
scripts: strip "AMD Instinct" from GPU name (#15668)
|
hai 4 meses |
|
compare-logprobs.py
|
c00ff929dc
scripts: add script to compare logprobs of llama.cpp against other frameworks (#17947)
|
hai 1 mes |
|
create_ops_docs.py
|
446595b9b3
Docs: add instructions for adding backends (#14889)
|
hai 5 meses |
|
debug-test.sh
|
e9b6350e61
scripts : make the shell scripts cross-platform (#14341)
|
hai 6 meses |
|
fetch_server_test_models.py
|
1d36b3670b
llama : move end-user examples to tools directory (#13249)
|
hai 8 meses |
|
gen-authors.sh
|
e9b6350e61
scripts : make the shell scripts cross-platform (#14341)
|
hai 6 meses |
|
gen-unicode-data.py
|
3fd62a6b1c
py : type-check all Python scripts with Pyright (#8341)
|
hai 1 ano |
|
get-flags.mk
|
a0c2dad9d4
build : pass all warning flags to nvcc via -Xcompiler (#5570)
|
hai 1 ano |
|
get-hellaswag.sh
|
e9b6350e61
scripts : make the shell scripts cross-platform (#14341)
|
hai 6 meses |
|
get-pg.sh
|
e9b6350e61
scripts : make the shell scripts cross-platform (#14341)
|
hai 6 meses |
|
get-wikitext-103.sh
|
e9b6350e61
scripts : make the shell scripts cross-platform (#14341)
|
hai 6 meses |
|
get-wikitext-2.sh
|
e9b6350e61
scripts : make the shell scripts cross-platform (#14341)
|
hai 6 meses |
|
get-winogrande.sh
|
e9b6350e61
scripts : make the shell scripts cross-platform (#14341)
|
hai 6 meses |
|
get_chat_template.py
|
5137da7b8c
scripts: corrected encoding when getting chat template (#11866) (#11907)
|
hai 11 meses |
|
hf.sh
|
e9b6350e61
scripts : make the shell scripts cross-platform (#14341)
|
hai 6 meses |
|
install-oneapi.bat
|
01684139c3
support SYCL backend windows build (#5208)
|
hai 1 ano |
|
serve-static.js
|
7ca5991d2b
ggml webgpu: add support for emscripten builds (#17184)
|
hai 1 mes |
|
server-bench.py
|
e81b8e4b7f
llama: use FA + max. GPU layers by default (#15434)
|
hai 4 meses |
|
sync-ggml-am.sh
|
f0c541d315
scripts : update sync scripts
|
hai 5 meses |
|
sync-ggml.last
|
0e59224990
sync : ggml
|
hai 1 mes |
|
sync-ggml.sh
|
f0c541d315
scripts : update sync scripts
|
hai 5 meses |
|
sync_vendor.py
|
ec18edfcba
server: introduce API for serving / loading / unloading multiple models (#17470)
|
hai 1 mes |
|
tool_bench.py
|
3c3635d2f2
server : speed up tests (#15836)
|
hai 4 meses |
|
tool_bench.sh
|
e9b6350e61
scripts : make the shell scripts cross-platform (#14341)
|
hai 6 meses |
|
verify-checksum-models.py
|
a2ac89d6ef
convert.py : add python logging instead of print() (#6511)
|
hai 1 ano |
|
xxd.cmake
|
1d36b3670b
llama : move end-user examples to tools directory (#13249)
|
hai 8 meses |
Shouyu
c45f89d551
ggml-hexagon: mm for mtmd (#17894)