| .. |
|
LlamaConfig.cmake.in
|
280345968d
cuda : rename build flag to LLAMA_CUDA (#6299)
|
hai 1 ano |
|
build-info.cmake
|
b38a16dfcf
cmake : fix issue with version info not getting baked into LlamaConfig.cmake (#3970)
|
%!s(int64=2) %!d(string=hai) anos |
|
build-info.sh
|
b12fa0d1c1
build : link against build info instead of compiling against it (#3879)
|
%!s(int64=2) %!d(string=hai) anos |
|
check-requirements.sh
|
f4ab2a4147
llama : fix BPE pre-tokenization (#6920)
|
hai 1 ano |
|
ci-run.sh
|
413e7b0559
ci : add model tests + script wrapper (#4586)
|
%!s(int64=2) %!d(string=hai) anos |
|
compare-commits.sh
|
0d56246f4b
ggml : group all experts in a single ggml_mul_mat_id (#6505)
|
hai 1 ano |
|
compare-llama-bench.py
|
e849648888
llama-bench : add pp+tg test type (#7199)
|
hai 1 ano |
|
convert-gg.sh
|
25423e9185
scripts : helper convert script
|
%!s(int64=2) %!d(string=hai) anos |
|
debug-test.sh
|
fed0108491
Scripting & documenting debugging one test without anything else in the loop. (#7096)
|
hai 1 ano |
|
gen-authors.sh
|
e11a8999b5
license : update copyright notice + add AUTHORS (#6405)
|
hai 1 ano |
|
gen-build-info-cpp.cmake
|
b38a16dfcf
cmake : fix issue with version info not getting baked into LlamaConfig.cmake (#3970)
|
%!s(int64=2) %!d(string=hai) anos |
|
gen-unicode-data.py
|
43248e5594
llama3 custom regex split (#6965)
|
hai 1 ano |
|
get-flags.mk
|
a0c2dad9d4
build : pass all warning flags to nvcc via -Xcompiler (#5570)
|
hai 1 ano |
|
get-hellaswag.sh
|
e9240cdfa0
scripts : add get-winogrande.sh
|
%!s(int64=2) %!d(string=hai) anos |
|
get-pg.sh
|
9a818f7c42
scripts : improve get-pg.sh (#4838)
|
%!s(int64=2) %!d(string=hai) anos |
|
get-wikitext-103.sh
|
50ccaf5eac
lookup: complement data from context with general text statistics (#5479)
|
hai 1 ano |
|
get-wikitext-2.sh
|
4bd0f93e4a
model: support arch `DbrxForCausalLM` (#6515)
|
hai 1 ano |
|
get-winogrande.sh
|
e9240cdfa0
scripts : add get-winogrande.sh
|
%!s(int64=2) %!d(string=hai) anos |
|
hf.sh
|
f4183afe6a
scripts : add --outdir option to hf.sh (#6600)
|
hai 1 ano |
|
install-oneapi.bat
|
01684139c3
support SYCL backend windows build (#5208)
|
hai 1 ano |
|
pod-llama.sh
|
280345968d
cuda : rename build flag to LLAMA_CUDA (#6299)
|
hai 1 ano |
|
qnt-all.sh
|
611363ac79
scripts : add pipefail
|
%!s(int64=2) %!d(string=hai) anos |
|
run-all-perf.sh
|
611363ac79
scripts : add pipefail
|
%!s(int64=2) %!d(string=hai) anos |
|
run-all-ppl.sh
|
611363ac79
scripts : add pipefail
|
%!s(int64=2) %!d(string=hai) anos |
|
run-with-preset.py
|
a2ac89d6ef
convert.py : add python logging instead of print() (#6511)
|
hai 1 ano |
|
server-llm.sh
|
280345968d
cuda : rename build flag to LLAMA_CUDA (#6299)
|
hai 1 ano |
|
sync-ggml-am.sh
|
e11a8999b5
license : update copyright notice + add AUTHORS (#6405)
|
hai 1 ano |
|
sync-ggml.last
|
7bd4ffb780
metal : fix warnings (skipme) (#0)
|
hai 1 ano |
|
sync-ggml.sh
|
e11a8999b5
license : update copyright notice + add AUTHORS (#6405)
|
hai 1 ano |
|
verify-checksum-models.py
|
a2ac89d6ef
convert.py : add python logging instead of print() (#6511)
|
hai 1 ano |
|
xxd.cmake
|
5cf5e7d490
`build`: generate hex dump of server assets during build (#6661)
|
hai 1 ano |
Georgi Gerganov
7bd4ffb780
metal : fix warnings (skipme) (#0)