| .. |
|
LlamaConfig.cmake.in
|
280345968d
cuda : rename build flag to LLAMA_CUDA (#6299)
|
há 1 ano atrás |
|
build-info.cmake
|
b38a16dfcf
cmake : fix issue with version info not getting baked into LlamaConfig.cmake (#3970)
|
há 2 anos atrás |
|
build-info.sh
|
b12fa0d1c1
build : link against build info instead of compiling against it (#3879)
|
há 2 anos atrás |
|
check-requirements.sh
|
04ac0607e9
python : add check-requirements.sh and GitHub workflow (#4585)
|
há 2 anos atrás |
|
ci-run.sh
|
413e7b0559
ci : add model tests + script wrapper (#4586)
|
há 2 anos atrás |
|
compare-commits.sh
|
0d56246f4b
ggml : group all experts in a single ggml_mul_mat_id (#6505)
|
há 1 ano atrás |
|
compare-llama-bench.py
|
33a5244806
compare-llama-bench.py: fix long hexsha args (#6424)
|
há 1 ano atrás |
|
convert-gg.sh
|
25423e9185
scripts : helper convert script
|
há 2 anos atrás |
|
gen-authors.sh
|
e11a8999b5
license : update copyright notice + add AUTHORS (#6405)
|
há 1 ano atrás |
|
gen-build-info-cpp.cmake
|
b38a16dfcf
cmake : fix issue with version info not getting baked into LlamaConfig.cmake (#3970)
|
há 2 anos atrás |
|
get-flags.mk
|
a0c2dad9d4
build : pass all warning flags to nvcc via -Xcompiler (#5570)
|
há 1 ano atrás |
|
get-hellaswag.sh
|
e9240cdfa0
scripts : add get-winogrande.sh
|
há 2 anos atrás |
|
get-pg.sh
|
9a818f7c42
scripts : improve get-pg.sh (#4838)
|
há 2 anos atrás |
|
get-wikitext-103.sh
|
50ccaf5eac
lookup: complement data from context with general text statistics (#5479)
|
há 1 ano atrás |
|
get-wikitext-2.sh
|
4bd0f93e4a
model: support arch `DbrxForCausalLM` (#6515)
|
há 1 ano atrás |
|
get-winogrande.sh
|
e9240cdfa0
scripts : add get-winogrande.sh
|
há 2 anos atrás |
|
hf.sh
|
f4183afe6a
scripts : add --outdir option to hf.sh (#6600)
|
há 1 ano atrás |
|
install-oneapi.bat
|
01684139c3
support SYCL backend windows build (#5208)
|
há 1 ano atrás |
|
pod-llama.sh
|
280345968d
cuda : rename build flag to LLAMA_CUDA (#6299)
|
há 1 ano atrás |
|
qnt-all.sh
|
611363ac79
scripts : add pipefail
|
há 2 anos atrás |
|
run-all-perf.sh
|
611363ac79
scripts : add pipefail
|
há 2 anos atrás |
|
run-all-ppl.sh
|
611363ac79
scripts : add pipefail
|
há 2 anos atrás |
|
run-with-preset.py
|
5f1925a8ce
scripts : move run-with-preset.py from root to scripts folder
|
há 2 anos atrás |
|
server-llm.sh
|
280345968d
cuda : rename build flag to LLAMA_CUDA (#6299)
|
há 1 ano atrás |
|
sync-ggml-am.sh
|
e11a8999b5
license : update copyright notice + add AUTHORS (#6405)
|
há 1 ano atrás |
|
sync-ggml.last
|
c4a3a4ff47
sync : ggml
|
há 1 ano atrás |
|
sync-ggml.sh
|
e11a8999b5
license : update copyright notice + add AUTHORS (#6405)
|
há 1 ano atrás |
|
verify-checksum-models.py
|
bedb92b603
scripts : use `/usr/bin/env` in shebang (#3313)
|
há 2 anos atrás |
slaren
0d56246f4b
ggml : group all experts in a single ggml_mul_mat_id (#6505)